agentleFS
snui1ssnui1s/losna-cli/skills/security-review/SKILL.MD

security-review

Skill1 starsChanged 2 months agoApache-2.0View on GitHub

1. Never claim "no validation exists" or "no check whatsoever" in any function without first reading the ENTIRE function. If claiming X is missing, you must state: "Read function [name] lines [start]-[end], found no check for X." 2. Every vulnerability reported MUST include the actual quoted code (not just a line number). If you cannot quote the exact code, do not report it as a finding. 3. Before claiming a path-traversal vulnerability exists, search the file for these patterns first:…

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use linkerd-patterns, dependency-cve-sweep and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • xfstudioSkill

    linkerd-patterns

    Implement Linkerd service mesh patterns for lightweight, security-focused service mesh deployments. Use when setting up Linkerd, configuring traffic policies, or implementing zero-trust networking with minimal overhead.

    Also in 5 projects that use this

  • berntpoppSkill

    dependency-cve-sweep

    Use when handling Dependabot PRs, CodeQL/Trivy alerts, or doing a routine dependency/CVE sweep for this repo.

    Also in 12 projects that use this

  • berntpoppSkill

    fleet-standard-adoption

    Use when bringing this repo into compliance with a GeneFoundry fleet standard (tool-naming, response-envelope, container-hardening, versioning, MCP transport, or logging) or closing its tracking issue.

    Also in 12 projects that use this

  • HABUBUSSSkill

    project-guidelines-example

    Also in 16 projects that use this

  • niloykumarbarmanSkill

    agent-sort

    Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

    Also in 13 projects that use this

  • royaluniondesign-sysSkill

    configure-ecc

    Interactive installer for Everything Claude Code — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files.

    Also in 11 projects that use this

  • +2 more from berntpopp

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 167 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never claim "no validation exists" or "no check whatsoever" in any function without first reading the ENTIRE function.

    line 6
  2. Distinctive:

    Every vulnerability reported MUST include the actual quoted code (not just a line number).

    line 10
  3. Distinctive:

    Before claiming a path-traversal vulnerability exists, search the file for these patterns first:

    line 13
  4. Distinctive:

    If any of these appear in the function, do NOT claim "no path validation exists" - instead evaluate whether the existing guard is …

    line 19
  5. Distinctive:

    Always distinguish between these two different situations:

    line 23
  6. Distinctive:

    Do not conflate these - they have very different severity.

    line 27
  7. Distinctive:

    Before finalizing the report, self-check every line that says "no X" or "lacks X" or "whatsoever" - if there's no quoted code proving the …

    line 46
  8. Distinctive:

    Never use vague phrases like "ไม่มีการป้องกันเลย" or "whatsoever" without code evidence backing it up.

    line 51

“Common” is measured: kept by at least 6 in 10 of the 167 edited versions of this file we could read. “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

Security Review Skill

Description: Use this whenever asked to review code for security vulnerabilities, do a security audit, or find exploits/weaknesses. Enforces evidence-based reporting to prevent hallucinated findings.

Rules for this task

  1. Never claim "no validation exists" or "no check whatsoever" in any function without first reading the ENTIRE function. If claiming X is missing, you must state: "Read function [name] lines [start]-[end], found no check for X."
  2. Every vulnerability reported MUST include the actual quoted code (not just a line number). If you cannot quote the exact code, do not report it as a finding.
  3. Before claiming a path-traversal vulnerability exists, search the file for these patterns first:
    • os.path.commonpath
    • os.path.realpath
    • os.path.abspath
    • startswith(base_dir) If any of these appear in the function, do NOT claim "no path validation exists" - instead evaluate whether the existing guard is sufficient, and explain why or why not with a concrete bypass example.
  4. Always distinguish between these two different situations:
    • "No guard exists at all" (must be proven by reading the whole function)
    • "A guard exists but can be bypassed" (must include a concrete input/command that demonstrates the bypass) Do not conflate these - they have very different severity.
  5. Severity levels:
    • Critical: exploitable with no existing guard at all (proven)
    • High: a guard exists but is bypassable with a realistic input (must show the bypass)
    • Medium: best practice gap, not directly exploitable
    • Low: code smell / maintainability, unrelated to security
  6. Report format for each finding:

    [Severity] Vulnerability name

    • Function: name (lines X-Y)
    • Code:
      <exact quoted code>
    • Problem: <explanation>
    • Example exploit (if applicable): <concrete bypass>
    • Fix: <specific recommendation>
  7. Before finalizing the report, self-check every line that says "no X" or "lacks X" or "whatsoever" - if there's no quoted code proving the absence, delete that claim or rephrase it as an open question instead ("should verify whether...").

Never use vague phrases like "ไม่มีการป้องกันเลย" or "whatsoever" without code evidence backing it up.

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.