Skills

zero-lab-ai/skills

Portable, evidence-bound security skills for authorized defensive assessment, red teaming, penetration testing, detection engineering, and engagement operations.

57 skills listed · Apache 2.0 · 286 stars · last pushed 15 Oct 2026

zero-lab-ai/skills on GitHub

Across these 57 skills

Pattern check

Nothing flagged in 51

Items to review in 6: agent-surface-audit, detection-engineering, detection-validate and 3 more

What it can touch

2 touch credentials
57 name web addresses
44 pre-approve tools
+3 more
- 6 run shell commands
- 6 bundle scripts
- 1 reaches the network

Checked at commit 1e2f93f on 3 Nov 2026.

Install the collection

6 of these skills have items to review. Read them before you install the whole collection.

Claude Code plugin

Installs the latest version, not the one we checked. Installs everything in the plugin, including any hooks, MCP servers and scripts our check doesn't cover.

claude plugin marketplace add zero-lab-ai/skills --scope user &&claude plugin install agent-security@zero-lab --scope user &&claude plugin install recon-operations@zero-lab --scope user &&claude plugin install identity-security@zero-lab --scope user &&claude plugin install application-endpoint-security@zero-lab --scope user &&claude plugin install network-protocol-security@zero-lab --scope user

Run /plugin to browse the other 5 plugins in it.

Any agent

Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.

npx skills@1.7.4 add zero-lab-ai/skills

Skills

All57 Items to review6

Skills in zero-lab-ai/skills
Skill	What it can touch	Pattern check	Licence	Updated
active-directory-attack-pathAnalyzes and prioritizes Active Directory and BloodHound attack paths using evidence freshness, disabled principals, prerequisites, authorization, operational noise, and remediation coverage. Use during an authorized red-team operation when reviewing AD graphs, nested groups, ACL abuse, delegation, sessions, GPO control, or routes to Tier Zero. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
adcs-exposure-auditAudits Active Directory Certificate Services configuration for dangerous certificate templates, PKI ACLs, enrollment interfaces, mapping policy, and identity escalation paths. Use during an authorized identity security review when assessing AD CS, certificate templates, enterprise CAs, or Certipy-style inventory without exercising an attack path. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
agent-action-proofGrades evidence for an AI agent's downstream actions without overstating what a callback, tool trace, file read, command result, or target change proves. Use when validating impact, writing findings, or reviewing agent test receipts. Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
agent-runtime-validationPlans and evaluates bounded runtime tests of AI agents, tools, memory, hooks, approvals, and scope enforcement. Use when static review is complete and an authorized assessment must determine how the deployed agent actually behaves. Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
agent-surface-auditReviews an MCP server's tool surface for tool poisoning, over-broad parameters, missing descriptions, and privilege escalation paths. Use when auditing, onboarding, or writing an MCP server, or when a user asks whether a server is safe to connect to an agent. Runs shell commands +4 more Pattern check: 2 items to reviewApache 2.0Updated 12 Oct 2026	Runs shell commands Reaches the network +3 more	Pattern check: 2 items to review	Apache 2.0	12 Oct 2026
agent-trust-boundary-auditMaps identity, authority, instruction, data, memory, and approval propagation across agents and agent-to-agent handoffs. Use when reviewing multi-agent systems, orchestrators, delegated tools, or confused-deputy exposure. Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
ai-surface-reconMaps an authorized AI system's externally observable models, retrieval paths, agent tools, guardrails, endpoints, and privileged consumers. Use when scoping an AI security assessment or building an evidence-bound attack-surface inventory. Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
ai-threat-modelBuilds an evidence-bound AI threat model from partial architecture, trust, identity, data-flow, and control information. Use when scoping an AI assessment, reviewing a design, or prioritizing realistic attack paths under uncertainty. Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
assessment-sequence-governanceValidates supplied immutable ordered manifests of opaque defensive assessment actions for authority, safeguards, evidence, and separate-operator review. Use when reviewing assessment sequencing without creating, changing, or executing actions. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
binary-fault-triageTriages supplied binary, crash, sanitizer, dump, static-analysis, and external reproduction evidence to distinguish a lead, observed fault, reproducible fault, security relevance, and demonstrated non-weaponized impact without executing, mutating, exploiting, or weaponizing a binary. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
binary-fault-validation-readinessGoverns an exact current binary-fault-triage assessment result and recorded validation-readiness handoff for separate isolated-lab review. Use when checking defensive authority, isolation, budget, stop, cleanup, custody, and independent-review readiness without analyzing faults, creating tests or inputs, determining exploitability, or authorizing execution or development. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
cloud-attack-pathMaps cloud identity and authorization paths across AWS, Azure, GCP, and hybrid trust boundaries, separating proven access from plausible and blocked routes. Use during an authorized cloud penetration test when tracing how a starting identity could assume roles, use credentials, execute workloads, cross providers, or reach sensitive data. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
command-channel-defense-assessmentAssesses supplied defensive evidence for prevention, visibility, detection, containment, and recovery coverage against opaque command-channel scenarios. Use when reviewing command-and-control exposure or control gaps without designing infrastructure, live tests, or operational guidance. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
covert-channel-assessmentAssesses covert-channel and data-egress exposure, then plans or records bounded purple-team validation with synthetic data. Use when evaluating DNS, web, cloud, ICMP, tunnel, timing, steganographic, or dead-drop paths without turning a plausible route into a claim of successful exfiltration. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
credential-exposure-auditAudits supplied evidence when passwords, hashes, private keys, browser or vault entries, cloud CLI credentials, application secrets, tokens, or credential-bearing artifacts may be exposed. Use for defensive review that must distinguish indicators from material and validity from privilege without decrypting, cracking, replaying, or authenticating. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
dataset-integrity-assessmentAudits dataset sources, labels, transformations, review, versioning, split integrity, retraining triggers, and rollback controls for poisoning and targeted degradation risk. Use when reviewing an ML training or evaluation data supply chain. Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
defensive-control-evidence-synthesisSynthesizes supplied evidence-backed defensive assessment results and administrative receipts into a scope-bound control-evidence matrix that preserves lineage, freshness, contradictions, unknowns, and gaps. Use when consolidating defensive control evidence without scanning, scoring, certifying, or rewriting findings. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
detection-engineeringBuilds detection rules that are proven before they ship — fire on known-bad, stay silent on known-good — and keeps false positives from blinding the SOC. Use when writing a Sigma/Suricata/YARA rule, reviewing a detection before deployment, triaging alert fatigue, or deciding whether a rule has earned production. Runs shell commands +3 more Pattern check: 1 item to reviewApache 2.0Updated 12 Oct 2026	Runs shell commands Names web addresses +2 more	Pattern check: 1 item to review	Apache 2.0	12 Oct 2026
detection-resilience-test-planPlans and records bounded defensive tests of whether preventive controls, telemetry, and detections remain effective across pre-approved opaque technique variations. Use when a blue or purple team needs authorization-, safety-, evidence-, cleanup-, and remediation-gated resilience measurement without generating bypass procedures, commands, payloads, or stealth rankings. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
detection-validateRuns attacker techniques and confirms whether detections actually fire, producing an honest ATT&CK coverage map that separates real gaps from accepted ones. Use when running a purple-team exercise, measuring detection coverage, validating that a SOC can see a technique, or turning 'we think we're covered' into evidence per technique. Runs shell commands +3 more Pattern check: 1 item to reviewApache 2.0Updated 12 Oct 2026	Runs shell commands Names web addresses +2 more	Pattern check: 1 item to review	Apache 2.0	12 Oct 2026
directory-persistence-auditAudits supplied sanitized directory-service governance evidence for durable control and persistence exposure without contacting live systems. Use when reviewing defensive directory control, baseline, monitoring, or exception evidence. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
engagement-report-assemblyAssembles supplied validated artifacts, immutable final findings, scope, methods, coverage, limitations, contradictions, and evidence indexes into a complete review-ready engagement package without rewriting, rescoring, hiding, closing, publishing, or contacting. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
example-auditReviews a supplied security artifact and reports supported findings. Use when an authorized assessment needs focused domain guidance. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
findings-reportWrites security findings that survive triage: reproducible, severity-justified, and fixable, in a fixed structure with a severity rubric. Use when turning a discovered vulnerability, misconfiguration, or weakness into a report entry, ticket, or disclosure. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
firmware-hardware-assessmentTracks embedded-device and firmware assessment coverage across exact units, acquisition methods, debug interfaces, stored secrets, update trust, radios, physical safety, and delegated external systems. Use when planning, conducting, reviewing, or handing over an authorized hardware or IoT penetration test. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
incident-validation-correlationCorrelates supplied sanitized incident observations with separately approved isolated defensive-validation receipts across prevent, observe, detect, contain, and recover. Use for defensive learning comparison without live response, hunting, technique design or execution, detection authoring, case management, findings, or reporting. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
kerberos-exposure-auditAudits supplied sanitized Kerberos governance evidence for policy, protection, monitoring, and evidence-handling exposure without contacting live systems. Use when reviewing a defensive Kerberos evidence package or assessing identity-control coverage. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
lateral-movement-mapMaps lateral movement candidates and multi-hop routes across Windows, Linux, network, DevOps, and cloud environments while separating transport reachability, authentication material, destination rights, authorization, execution proof, resulting access, detection exposure, and cleanup. Use when planning or documenting remote access paths after a foothold. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
lateral-movement-readinessReviews an already-supplied lateral movement candidate for exact upstream map binding, authorization, non-production isolation, containment, telemetry, stop control, rollback, cleanup ownership, custody, tool governance, and a separate-validation handoff. Use before transferring a candidate to a lab validation team. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
memory-forensics-triageTriages supplied Windows, Linux, or other volatile-memory images while preserving acquisition provenance, image integrity, process and region evidence, network and object correlations, extracted-artifact custody, timeline limits, and claim confidence. Use for offline memory-forensics review and handoff, not live rootkit trust assessment or full malware reverse engineering. Touches credentials +2 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Touches credentials Names web addresses +1 more	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
ml-decision-boundary-assessmentEvaluates classifiers and scoring models used as security gates for adversarial robustness, preprocessing differences, thresholds, abstention, and fallback behavior. Use when an authorized assessment must measure whether bounded input changes alter a security decision. Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
mobile-application-assessmentTracks Android and iOS application assessment coverage across packages, platform components, local storage, device behavior, WebViews, native code, network trust, and delegated backend APIs. Use when planning, conducting, reviewing, or handing over an authorized mobile app penetration test. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
model-artifact-lifecycle-auditAudits how model artifacts are accepted, validated, stored, selected, loaded, executed, monitored, and retired. Use when reviewing model registries, loaders, CI/CD pipelines, scanner-to-runtime gaps, or ML supply-chain controls. Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
model-serving-exposure-auditAudits model-serving APIs, administrative and debug surfaces, vector stores, object storage, caches, workload identity, metadata access, and orchestration credentials. Use when reviewing the deployed infrastructure around model inference. Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
network-reconPlans authorized network reconnaissance, checks proposed targets against explicit IP scope, chooses scanning tools by cost, and audits completed scans for coverage. Use when mapping a network, enumerating hosts and services, deciding which scanner to run, or determining whether an empty scan is a finding or a failure. Runs shell commands +3 more Pattern check: 1 item to reviewApache 2.0Updated 12 Oct 2026	Runs shell commands Names web addresses +2 more	Pattern check: 1 item to review	Apache 2.0	12 Oct 2026
opsec-planningBuilds red-team OPSEC plans that connect an authorized objective to observable artifacts, detection risk, countermeasures, abort conditions, cleanup, and post-operation review. Use before a significant action or attack chain when stealth matters, when choosing between noisy and quiet approaches, or when an operator needs an auditable go/no-go decision. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
osint-scannerMaps a target's public footprint — infrastructure, tech stack, leaked credentials, and people — using third-party data so no packet reaches the target. Use when scoping an engagement, planning a phishing pretext, or doing reconnaissance where the target must not detect it, and when deciding whether a recon action actually touches the target or not. Runs shell commands +3 more Pattern check: 1 item to reviewApache 2.0Updated 12 Oct 2026	Runs shell commands Names web addresses +2 more	Pattern check: 1 item to review	Apache 2.0	12 Oct 2026
password-audit-planPlans authorized offline password-strength audits across supplied hash datasets while enforcing compute budgets, progressive pass order, cohort coverage, aggregate-only reporting, and restricted handling. Use when preparing or documenting password cracking without online authentication, spraying, stuffing, replay, or credential reuse testing. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
persistence-surface-assessmentMeasures local Windows and Linux endpoint persistence exposure from supplied evidence by deriving consumer, authority, lifecycle, prevention, context, telemetry, and coverage state. Use when auditing durable-execution risk without creating, activating, testing, ranking, or removing a persistence mechanism. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
physical-reconAssesses supplied daylight physical-security observations from authorized public vantage points at opaque site and control level. Use when reviewing physical reconnaissance without entering property, tracking people, collecting identifiers, planning approaches, or generating intrusion methods. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
privilege-escalation-assessmentAssesses and ranks Windows, Linux, and cloud privilege-escalation paths using observed prerequisites, execution authority, operational signal, reliability, risk, cleanup, and verification. Use after gaining an authorized foothold or cloud identity when deciding whether elevation is necessary and which candidate path is defensible. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
prompt-injection-assessmentAssesses whether direct, indirect, multi-turn, retrieved, or tool-mediated instructions can override an AI system's intended policy or scope. Use when conducting an authorized prompt-injection test with benign canaries and evidence-bound outcomes. Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 15 Oct 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	15 Oct 2026
protocol-exploitation-assessmentAssesses network protocol exploitation candidates while separating observed service behavior, advisory applicability, reproduced faults, demonstrated impact, authorization, disruption risk, telemetry, and coverage. Use when a banner, scanner result, packet trace, reset, legacy protocol, or suspected handshake weakness needs a defensible validation plan. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
protocol-traffic-analysisAnalyzes supplied PCAP and packet-capture evidence into hosts, conversations, dependencies, authentication exposure, timing patterns, blind spots, and defensible follow-up. Use when reviewing network traffic without transmitting to the observed systems. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
rag-data-exposure-auditAssesses document authorization, tenant isolation, raw-chunk fields, citations, caches, exports, and sensitive-source leakage in retrieval systems. Use when an authorized RAG assessment must determine what data each identity can retrieve or disclose. Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
rag-surface-reconMaps an authorized retrieval system's sources, connectors, chunking, embeddings, indexes, filters, ranking, caches, citations, and exposed retrieval fields. Use when scoping a RAG security assessment or explaining observed retrieval behavior. Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
recon-automation-governanceGoverns supplied reconnaissance job manifests with exact authority and scope binding, contact receipts, bounded waves and budgets, controlled retries, tested stop controls, custody, and defensive handoff. Use when reviewing or recording scheduled recon automation without generating commands, choosing targets, running reconnaissance, or expanding scope. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
retrieval-integrity-assessmentAssesses whether an authorized retrieval-augmented AI system preserves source, index, retrieval, context, and output integrity. Use when testing RAG poisoning, retrieval hijacking, context saturation, semantic substitution, or citation controls with benign canaries. Names web addresses Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
rootkit-triageTriages suspected rootkits, bootkits, hidden processes, kernel hooks, driver or module anomalies, concealed network activity, eBPF implants, and boot-integrity failures. Use when host tools may be lying and the incident needs evidence-preserving cross-view analysis, containment, or forensic handoff. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026
security-test-tool-governanceGoverns supplied benign security-test tool artifacts through purpose, authority, provenance, artifact integrity, safety-test evidence, version-bound review, custody, change control, and defensive handoff. Use when reviewing proposed security tooling or deciding whether an externally supplied artifact is ready for an authorized isolated test, without generating source code, payloads, build procedures, bypasses, or deployment instructions. Names web addresses +1 more Pattern check: Nothing flaggedApache 2.0Updated 12 Oct 2026	Names web addresses Pre-approves tools	Pattern check: Nothing flagged	Apache 2.0	12 Oct 2026