cloud-saas-exposure is a skill in elementalsouls/Claude-OSINT, last changed 24 Aug 2026. It can touch credentials, change agent settings, run shell commands, reach the network and name web addresses — read the findings before installing.
Organization-grade cloud and supply-chain attack-surface discovery: S3/GCS/Azure Blob bucket discovery via observed-name mining (CNAME/cert-SAN/Wayback) and bounded two-class permutation (6 prefixes x 15 suffixes on trusted tokens, bounded target-bound expansion on subdomain stems), existence (HEAD/GET) vs public-listing confirmation, object-key triage into 9 value tiers (database dumps, credentials, IaC state, kubeconfig, VCS dirs, config, archives, PII, logs), dangling-CNAME bucket-takeover detection, and the ownership-gated severity model that stops an unattributable public bucket from becoming a false CRITICAL; the fully offline AWS-account-ID recovery from a leaked AKIA/ASIA/AROA access key (base32 decode, runnable stdlib Python, canonical test vector, AWS-documentation-example-ID screening); dependency-confusion confirmation for npm/PyPI (internal-signal classifier -- private-registry binding vs org-namespace match -- paired with a read-only public-registry 404 check and the npm scope-claimability nuance the public search API misses); and passive cloud-native/container/Kubernetes/CI control-plane fingerprinting (Lambda URLs, API Gateway, Cloud Run, App Service, kubelet/etcd/K8s API/dashboard, Jenkins/GitLab/Argo CD) as an org-attribution and exposure surface. Passive/discovery only -- no exploitation, no credential submission, no active control-plane confirmation (a stage-6 validate_cloud active tier is described but out of scope). Use when enumerating a target's cloud storage footprint, recovering an AWS account ID from a leaked key, confirming a supply-chain dependency-confusion vector, or fingerprinting cloud-native/K8s/CI infrastructure for an authorized external recon engagement.
At a glance
What it can touch
How much a skill can do, not whether it is risky.
Pattern check
1 item to review
Instruction-override phrases
R23 · High · SKILL.md:220Commit c359ec1 · 20 Nov 2026
How the check worksPattern check:1 item to reviewSee it
QAI Index
We rate every listed skill the same way, from 0 to 100.
A guide to compare by, not a verdict on the skill.
How it's scoredGet an email when its check changes.
Keep it with the other skills you use, installed with one command.
Install
Sign in to see how to install it
Free with Google or an email link, no password needed. Then pick your agent and copy its steps.
What it can touch
Sign in to see the file and line behind each one
The summary at the top stays open to everyone. Signing in is free, with Google or an email link.
Pattern check
Pattern check: 1 item to review · commit c359ec1 · 20 Nov 2026
We checked every text file in this skill, at commit c359ec1 on 20 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.
How the check worksReport an incorrect finding
Outside links we did not follow
- https://storage.googleapis.com/
- https://$
- https://storage.googleapis.com/$
- https://$Name.s3.amazonaws.com/
- https://storage.googleapis.com/$Name
- https://$Name.blob.core.windows.net/?comp=list
- https://hackingthe.cloud/aws/enumeration/account_id_from_keys/
- https://www.npmjs.com/org/
- https://www.npmjs.com/
- https://registry.npmjs.org/acme-internal-utils
Show 4 more
- https://registry.npmjs.org/@acme%2Fdesign-system
- https://www.npmjs.com/org/acme
- https://www.npmjs.com/~acme
- https://pypi.org/pypi/acme-internal-tools/json
Format check
Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.
Agent Skills specFails
The format our Agent Skills docs set out, held to the strictest version of each rule among the agents we check.
- Error
The description is 1,719 characters; the limit is 1,024. D2
Fix: Shorten it to 1,024 characters or fewer, and move detail into the body.
- Warning
Fields outside the spec: version, sources and triggers. Uploads to the Claude apps and API, and strict validators, reject the file; most agents ignore these fields. O1
Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.
- Warning
The body is 750 lines; the spec suggests under 500. B1
Fix: Move detailed sections into reference files and link to them from SKILL.md.
- Warning
The body is about 10,315 tokens (approx.); the spec suggests under 5,000. B2
Fix: Move detail into reference files that the agent reads only when needed.
- Note
The first sentence of the description is 1285 characters. Agents shorten long descriptions, so lead with the main job. D8
Fix: Start with one short sentence that names the job.
- Note
There is no license field, so readers can't tell whether they may reuse the skill. O2
Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.
- Error
Claude CodePasses with warnings
Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.
- Warning
The description comes to 1,719 characters; Claude Code's skill listing cuts each entry at 1,536. The listing keeps every skill's name, but past its budget (1% of the context window) Claude Code drops descriptions, starting with the skills used least. D5
Fix: Put the key use case first, or move detail into the body.
- Note
The first sentence of the description is 1285 characters. Agents shorten long descriptions, so lead with the main job. D8
Fix: Start with one short sentence that names the job.
- Note
Claude Code ignores fields it doesn't know: version, sources and triggers. O1
Fix: Check the spelling against Claude Code's field list, or delete them.
- Note
The body is 750 lines; the spec suggests under 500. Claude Code's docs say the same. B1
Fix: Move detailed sections into reference files and link to them from SKILL.md.
- Note
The body is about 10,315 tokens (approx.); the spec suggests under 5,000. After compaction Claude Code keeps only the first 5,000 tokens of a skill. B2
Fix: Move detail into reference files that the agent reads only when needed.
- Warning
Claude apps & API uploadFails
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Error
The description is 1,719 characters; the limit is 1,024. Anthropic's validator rejects it. D2
Fix: Shorten it to 1,024 characters or fewer, and move detail into the body.
- Error
Upload and packaging fail on fields outside the spec: version, sources and triggers. O1
Fix: Delete them, and keep your own data under metadata as text values.
- Note
The body is 750 lines; the spec suggests under 500. Anthropic's guidance says the same. B1
Fix: Move detailed sections into reference files and link to them from SKILL.md.
- Note
The body is about 10,315 tokens (approx.); the spec suggests under 5,000. Anthropic's guidance says the same. B2
Fix: Move detail into reference files that the agent reads only when needed.
- Error
OpenAI (Codex & API)Fails
Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.
- Error
The description is 1,719 characters; the limit is 1,024. Codex has no limit, but OpenAI's upload follows the spec. D2
Fix: Shorten it to 1,024 characters or fewer, and move detail into the body.
- Warning
Fields outside the spec: version, sources and triggers. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1
Fix: Delete them, or move your own data under metadata as text values.
- Note
The first sentence of the description is 1285 characters. Agents shorten long descriptions, so lead with the main job. D8
Fix: Start with one short sentence that names the job.
- Error
VS Code & CopilotPasses with warnings
VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.
- Warning
The description is 1,719 characters; the limit is 1,024. VS Code cuts it at 1,024 characters. D2
Fix: Shorten it to 1,024 characters or fewer, and move detail into the body.
- Note
VS Code ignores fields it doesn't support: version, sources and triggers. O1
Fix: Delete them unless another agent you target reads them.
- Warning
SKILL.md
We don't show this file's text because our check flagged hidden or instruction-override text in it.
Read SKILL.md on GitHub (opens in a new tab)Files
2 files
| Path | Size |
|---|---|
| README.md (opens in a new tab) | 7 KB |
| SKILL.md (opens in a new tab) | 43.7 KB |
Changelog
Newest first: each commit that changed its folder on GitHub, and each change to its listing here.
- Listed on QAI
- Updated: feat(grounding): require sources: on all skills (#25) (f4acf9e (opens in a new tab))
- Updated: ci: fix markdownlint config loading + osint-autopilot frontmatter (#18) (66ffd91 (opens in a new tab))
- Updated: chore(skills): genericize private product references across the library (5677cb6 (opens in a new tab))
- Updated: feat(skills): add Tier-2 org-grade OSINT skills — continuous monitori… (eccfab4 (opens in a new tab))
QAI Index badge
Show this skill's QAI Index in a README or on a website. It links back to this page and changes when we refresh the catalog.
[](https://qai.io/skills/elementalsouls/claude-osint/cloud-saas-exposure)More from elementalsouls/Claude-OSINT
| Skill | QAI Index | What it can touch | Pattern check | Licence | Updated |
|---|---|---|---|---|---|
| 56/QI |
| Pattern check: Nothing flagged | MIT | 24 Aug 2026 | |
| 56/QI |
| Pattern check: Nothing flagged | MIT | 24 Aug 2026 | |
| 56/QI |
| Pattern check: Nothing flagged | MIT | 24 Aug 2026 | |
| 51/QI |
| Pattern check: 1 item to review | MIT | 24 Aug 2026 | |
osint-autopilotEnd-to-end external OSINT engagement autopilot. Run the FULL osint-methodology pipeline to completion in ONE go for an authorized domain — engagement folder, Stages 1-5 (seed, expansion, enrichment, exposure, convergence), multi-agent per-host content+JS fan-out, headline verification, auto-generated findings, and a consolidated multi-tab .xlsx deliverable. Stops ONLY for Stage 6 (active exploitation) arming and out-of-scope sibling assets. Use whenever asked to "run OSINT / recon / attack-surface" on a target — do NOT deliver a thin passive first pass. 61/QI
Pattern check: Nothing flaggedMITUpdated 24 Aug 2026 | 61/QI |
| Pattern check: Nothing flagged | MIT | 24 Aug 2026 |
| 61/QI |
| Pattern check: Nothing flagged | MIT | 24 Aug 2026 |
Other Cloud & DevOps skills
Same category, most repo stars first.