agentleFS
Sign inStart free
browozbrowoz/agentic-sdlc-skills/skills/agentic-security-review/SKILL.md

agentic-security-review

Skill4 starsChanged 5 months agoMITView on GitHub

Run a security and dependency audit for agent systems, tool-using AI apps, MCP/A2A integrations, or security-sensitive AI-generated code. Check slopsquatting risk, tool shadowing, rug pulls, memory/context poisoning, secrets, unsafe permissions, and common CWE patterns. Use when asked for security review, dependency audit, vulnerability check, MCP tool safety, or production merge safety. Do NOT use for general code review, style issues, feature work, performance tuning, or non-security bugs.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Luis85/agentic-workflow★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to find security risks introduced by agentic code, AI-generated changes, tool access, or untrusted context.

    line 15
  2. Very specific:

    Run scripts/check_deps.py <project-root> when Python files are present.

    line 29
  3. Distinctive:

    Every high/critical finding has a reproduction path or clear evidence.

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Agentic Security Review

Use this skill to find security risks introduced by agentic code, AI-generated changes, tool access, or untrusted context. Scope the review before scanning.

Workflow

  1. Determine scope:
    • deps-only: package declarations, lockfiles, imports.
    • code-only: secrets, auth, input handling, injection risks.
    • full: dependencies, code, tools, memory, context, red-team cases.
  2. Classify rigor:
    • Prototype: dependency and secret checks.
    • Internal: dependency, secret, input validation, and tool permission checks.
    • Production: full review plus context poisoning, CaMeL-style separation decision, red-team scenarios, and release blockers.
  3. Run scripts/check_deps.py <project-root> when Python files are present.
  4. Fill SECURITY_REVIEW.md from assets/templates/SECURITY_REVIEW.md.
  5. Mark findings with severity, evidence, file path, and concrete fix.
  6. Block release only for exploitable or high-impact issues; otherwise provide prioritized remediation.

Focus Areas

  • Dependencies: undeclared imports, unpinned direct dependencies, missing lockfile, suspicious package names.
  • Tools: shadowing, broad credentials, unsafe side effects, unclear provenance.
  • Code: CWE-20, CWE-78, CWE-89, CWE-327, hardcoded secrets, weak auth.
  • Context: prompt injection through external data, memory poisoning, unsafe tool responses, mixed trusted/untrusted data.

References

Read ../agentic-engineering-sdlc/references/day2_tools_and_interop.md for tool risks and ../agentic-engineering-sdlc/references/day4_security_and_evaluation.md for security/evaluation depth.

Done Criteria

  • Scope, rigor, and exclusions are documented.
  • Script output is attached or summarized when applicable.
  • Release blockers are separated from hardening recommendations.
  • Every high/critical finding has a reproduction path or clear evidence.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free