Skills

oma-security

oma-security is a skill in first-fluke/oh-my-agent, last changed 27 Oct 2026. It can run shell commands and name web addresses. Our pattern check flagged nothing at commit 9735136 on 27 Oct 2026.

Pattern check: nothing flagged · commit 9735136 · 27 Oct 2026

Install
From the author
Scan application source, agent skills, and MCP components; run penetration tests against scoped web test deployments, validate findings, and configure scan gates. Use oma-qa for broad quality reviews and domain skills for remediation.
Licence
MIT
Repo stars
1.4k
Folder last changed
27 Oct 2026 (opens in a new tab)
Publisher
first-fluke
Files
12 files
Checked
9735136 (opens in a new tab) · 27 Oct 2026

Install

Each tab says whether it installs commit 9735136, the one we checked, or the latest version.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.

Pinned to commit 9735136, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/first-fluke/oh-my-agent.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 9735136cabdf8479885a68018561eb30a81186c6 &&
  git -C "$tmp" sparse-checkout set -- .agents/skills/oma-security &&
  git -C "$tmp" checkout -q 9735136cabdf8479885a68018561eb30a81186c6 &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/oma-security &&
  cp -R "$tmp"/.agents/skills/oma-security/. .claude/skills/oma-security/ &&
  rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Claude Code docs (opens in a new tab)

What it can touch

From the files and frontmatter at commit 9735136. This is how much a skill can do, not whether it is risky.

What it can touch: Scripts or outside hosts

  • Runs shell commands

    Its instructions or files give the agent commands to run on your computer.

  • Names web addresses

    It mentions outside web addresses the agent may visit. We list them but don't follow them.

Pattern check

Pattern check: nothing flagged · commit 9735136 · 27 Oct 2026

We checked every text file in this skill, at commit 9735136 on 27 Oct 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://github.com/Autumn-27/Autumn-27/blob/main/README.md
  • https://github.com/Hinln/ARTEX
  • https://github.com/jiwoochris/artex-ko
  • https://github.com/Hinln/ARTEX/blob/main/cmd/artex/main.go
  • https://github.com/Hinln/ARTEX/blob/main/docker-compose.yml
  • https://github.com/vercel-labs/deepsec/blob/main/docs/reviewing-changes.md
  • https://github.com/cisco-open/ai-deep-sast/blob/main/deepscan.py
  • https://cisco-ai-defense.github.io/docs/skill-scanner/results-and-tuning
  • https://github.com/cisco-ai-defense/mcp-scanner
  • https://github.com/cloudflare/security-audit-skill/blob/main/skills/security-audit/VALIDATION-AND-REPORTING.md
Show 19 more
  • https://github.com/cisco-open/ai-deep-sast
  • https://github.com/cisco-open/ai-deep-sast/blob/main/README.md
  • https://github.com/cisco-open/ai-deep-sast/blob/main/indexer.py
  • https://github.com/cisco-open/ai-deep-sast/blob/main/detector.py
  • https://github.com/cisco-open/ai-deep-sast/blob/main/coverage_guide.py
  • https://github.com/cisco-open/ai-deep-sast/blob/main/finding_store.py
  • https://github.com/cisco-open/ai-deep-sast/blob/main/deepscan_reporter.py
  • https://github.com/cisco-open/ai-deep-sast/blob/main/Jenkinsfile
  • https://github.com/cisco-open/ai-deep-sast/blob/main/triager.py
  • https://json-schema.org/draft/2020-12/schema
  • https://github.com/cisco-ai-defense/mcp-scanner/blob/main/mcpscanner/cli.py
  • https://github.com/cisco-ai-defense/mcp-scanner/blob/main/README.md
  • https://github.com/cisco-ai-defense/skill-scanner
  • https://github.com/cisco-ai-defense/skill-scanner/blob/main/docs/getting-started/quick-start.md
  • https://github.com/cisco-ai-defense/skill-scanner/blob/main/docs/user-guide/installation-and-configuration.md
  • https://github.com/cisco-ai-defense/skill-scanner/blob/main/docs/architecture/analyzers/behavioral-analyzer.md
  • https://cisco-ai-defense.github.io/docs/skill-scanner/llm-providers
  • https://cisco-ai-defense.github.io/docs/skill-scanner/recommended-settings
  • https://github.com/cisco-ai-defense/skill-scanner/blob/main/README.md#scope-and-limitations

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 specPasses

    The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

    • 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.

    • Note

      Reference files over 100 lines with no table of contents at the top: resources/artex.md (109 lines), resources/ci.md (135 lines), resources/cisco-source.md (109 lines), resources/findings-contract.md (409 lines), resources/mcp-scanning.md (123 lines) and 1 more. B5

      Fix: Add a short list of the sections at the top of each.

  • Claude CodePasses

    Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

    • Note

      Reference files over 100 lines with no table of contents at the top: resources/artex.md (109 lines), resources/ci.md (135 lines), resources/cisco-source.md (109 lines), resources/findings-contract.md (409 lines), resources/mcp-scanning.md (123 lines) and 1 more. B5

      Fix: Add a short list of the sections at the top of each.

  • Claude apps & API uploadPasses

    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.

    • Note

      The description is 234 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

      Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

    • Note

      Reference files over 100 lines with no table of contents at the top: resources/artex.md (109 lines), resources/ci.md (135 lines), resources/cisco-source.md (109 lines), resources/findings-contract.md (409 lines), resources/mcp-scanning.md (123 lines) and 1 more. B5

      Fix: Add a short list of the sections at the top of each.

  • OpenAI (Codex & API)Passes
  • VS Code & CopilotPasses

SKILL.md

Files

12 files

PathSize
SKILL.md (opens in a new tab)15.1 KB
resources/artex.md (opens in a new tab)9.1 KB
resources/ci.md (opens in a new tab)11.1 KB
resources/cisco-source.md (opens in a new tab)8.3 KB
resources/deepsec-config.md (opens in a new tab)3 KB
resources/deepsec-matchers.md (opens in a new tab)2.4 KB
resources/deepsec-scanning.md (opens in a new tab)2.7 KB
resources/deepsec-setup.md (opens in a new tab)2.9 KB
resources/findings-contract.md (opens in a new tab)27.6 KB
resources/mcp-scanning.md (opens in a new tab)8 KB
resources/skill-scanning.md (opens in a new tab)7.8 KB
resources/validation.md (opens in a new tab)8 KB

Copies

These share its SKILL.md or its name and description but not all its files, so we list them separately.

More from first-fluke/oh-my-agent

  • oma-academic-writing

    first-fluke/oh-my-agent

    Draft and revise academic prose against a rubric, evidence, and citation requirements. Use for essays, reports, literature reviews, or academic style audits.

    • Runs shell commands
    Pattern check: Nothing flagged

    MIT · 1.4k repo stars · Updated 27 Oct 2026

  • oma-academic-writing

    first-fluke/oh-my-agent

    Draft and revise academic prose against a rubric, evidence, and citation requirements. Use for essays, reports, literature reviews, or academic style audits.

    • Instructions only
    Pattern check: Nothing flagged

    MIT · 1.4k repo stars · Updated 4 Oct 2026

  • oma-architecture

    first-fluke/oh-my-agent

    Evaluate system boundaries and architectural tradeoffs. Use for architecture decisions, design reviews, and ADRs.

    • Runs shell commands
    Pattern check: Nothing flagged

    MIT · 1.4k repo stars · Updated 27 Oct 2026

  • oma-architecture

    first-fluke/oh-my-agent

    Evaluate system boundaries and architectural tradeoffs. Use for architecture decisions, design reviews, and ADRs.

    • Runs shell commands
    Pattern check: Nothing flagged

    MIT · 1.4k repo stars · Updated 15 Oct 2026

  • oma-backend

    first-fluke/oh-my-agent

    Implement server APIs, authentication, and application data access. Schema modeling and query tuning use oma-db.

    • Runs shell commands
    • Names web addresses
    • +1 more
    Pattern check: Nothing flagged

    MIT · 1.4k repo stars · Updated 27 Oct 2026

  • oma-backend

    first-fluke/oh-my-agent

    Implement server APIs, authentication, and application data access. Schema modeling and query tuning use oma-db.

    • Runs shell commands
    • Names web addresses
    • +1 more
    Pattern check: Nothing flagged

    MIT · 1.4k repo stars · Updated 27 Oct 2026

All skills in first-fluke/oh-my-agent