dependency-check
Skill1 starsChanged 30 days agoMITView on GitHub
Audit project dependencies for vulnerabilities, outdated packages, and compatibility issues. Optionally apply safe updates with test validation. Use periodically or before release.
- Installs packages
9 other projects use a version of this.
Adopted by
Most recently taken up by
- MELJOESTEIN/agentic-devsecops-kittheir own version, first seen Oct 20, 2026
- kitloomlk-stack/code-review-security-kittheir own version, first seen Oct 15, 2026
- dfedoryshchev/weftworkstheir own version, first seen Oct 13, 2026
- Qualimetry/qualimetry-ai-skillstheir own version, first seen Sep 4, 2026
- neronain/ClaudeSkills-Neronaintheir own version, first seen Aug 9, 2026
- NovaCode37/claude-security-skillstheir own version, first seen Jun 7, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- NovaCode37/claude-security-skills★ 13same name
- dfedoryshchev/weftworks★ 5same name
- neronain/ClaudeSkills-Neronain★ 3same name
- DonTizi/CodeGeass★ 2same name
- jpoindexter/theft-kit★ 1same name
- Qualimetry/qualimetry-ai-skills★ 1same name
- khanashes/claude-skills★ 0same name
- kitloomlk-stack/code-review-security-kit★ 0same name
- MELJOESTEIN/agentic-devsecops-kit★ 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 repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- audit-projectSkill
- cleanupSkill
- create-skillSkill
- dailySkill
- documentSkill
- execute-prpSkill
- ez-project-workflowSkill
- fix-issueSkill
- generate-prpSkill
- housekeepingSkill
- kickoffSkill
- monitor-setupSkill
- nextSkill
- performanceSkill
- pipelineSkill
- refactorSkill
- retrospectiveSkill
- review-codeSkill
- rollbackSkill
- security-scanSkill
- statusSkill
- tddSkill
- upgrade-statusSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 6 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Read pyproject.toml for declared dependencies
- Distinctive: line 10
Read CLAUDE.md / AGENTS.md for tech stack context
- Very specific: line 11
Check that pip-audit is installed (suggest pip install pip-audit otherwise)
- Distinctive: line 14
Run in this order:
- Very specific: line 31
Run the test suite: pytest tests/ -v
- Distinctive: line 32
If tests fail, revert that update and flag it
- Distinctive: line 38
Ask the user for the call
- Very specific: line 41
Always check pip-audit is installed before scanning
- Distinctive: line 42
Always run tests after each update
- Distinctive: line 43
Never update a major version without user approval
“Common” is measured: kept by at least 6 in 10 of the 7 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.
Files
Dependency Check
Phase 1: Read state
- Read
pyproject.tomlfor declared dependencies - Read
CLAUDE.md/AGENTS.mdfor tech stack context - Check that
pip-auditis installed (suggestpip install pip-auditotherwise)
Phase 2: Analyze
Run in this order:
pip-audit 2>&1— vulnerability scanpip list --outdated 2>&1— outdated packages- Compatibility check — for each outdated package, look at its changelog for breaking changes since the current pinned version
Phase 3: Report
Produce a structured report:
- CRITICAL vulnerabilities (require immediate action)
- HIGH vulnerabilities
- Updates available — organized by risk:
- SAFE: patch-level only (1.2.3 -> 1.2.4)
- MODERATE: minor (1.2.x -> 1.3.x)
- RISKY: major (1.x -> 2.x)
Phase 4: Optionally apply (if user passes --fix or approves)
- Apply SAFE updates only — patch versions to pyproject.toml
- Run
pip install -e ".[dev]" - Run the test suite:
pytest tests/ -v - If tests fail, revert that update and flag it
- Report what was updated and what was skipped
For CRITICAL vulnerabilities without a safe fix:
- Explain the risk
- Propose a workaround or migration plan
- Ask the user for the call
Rules
- Always check
pip-auditis installed before scanning - Always run tests after each update
- Never update a major version without user approval
- Revert updates that break tests — leave the project in a working state
- Pin exact versions in pyproject.toml (no ranges for prod deps)
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
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.

