agentsclimarketplace

Automated security review

Skill K95M65/AI_ONBOARD/skills/automated-security-review

Portable agent workflow framework for Codex, Claude Code, and OpenCode—shared project context, focused skills, independent review, and safe updates.

Install
npx -y skills add K95M65/AI_ONBOARD --skill automated-security-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 19 days oldThe repository was created 19 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Wire automated security scanning into CI so every pull request is scanned for vulnerable dependencies, committed secrets, and code weaknesses. Use when setting up or improving a project's security gates in GitHub Actions.

SKILL.md

1.7 KB, as published. Nobody here has run it

Automated security review

Turns the manual security skills into a standing gate: what dependency-vuln-scan, secret-scan, and a SAST run do by hand, run automatically on every PR.

When to use

Setting up (or hardening) a repo's CI security checks.

Steps

  1. Generate a starter GitHub Actions workflow: 
    bash scripts/gen-workflow.sh [.github/workflows]
    It writes security.yml with three jobs: dependency scan (npm audit / govulncheck), secret scan (gitleaks, full history), and SAST (Semgrep). Refuses to overwrite an existing file.
  2. Adapt it to your stack: enable the ecosystem jobs you use, set severity thresholds, and decide which jobs block the merge vs report only.
  3. Require the check in branch protection so failures actually gate the merge.
  4. Keep the human lens too: automated scans catch known patterns; the security-review subagent and security-audit skill catch logic/authz bugs that scanners miss. Automation is the floor, not the ceiling.

What to gate on

  • Block: committed secrets (any), new Critical/High dependency CVEs, SAST High findings.
  • Report: Medium/Low — surface without blocking, triage in review.

Notes

  • The workflow pins actions and runs on pull_request + push to the default branch.
  • False positives are expected — tune ignore files (.gitleaksignore, Semgrep rule selection) rather than disabling a whole job.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.