security-audit

security-audit is an Application security skill for AI agents, published by shopsys in the shopsys repository on GitHub. Skillspace rates security-audit D (60/100) and the safety scan flagged it for review; the rating is based on static analysis only.

Shopsys-specific AI security audit of a pull request diff. Reviews changed code for real, exploitable security issues against OWASP Top 10 / CWE, grounded in how this repo implements each control. Runs the built-in /security-review as a high-confidence baseline, then layers Shopsys-specific checks, and posts findings as inline PR comments plus one summary comment. Use in CI on pull requests, or locally to audit branch changes.

Grade
D
Quality
60 / 100
Safety
Needs review
GitHub stars
349

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubshopsys/shopsys

Our review

Architecture
73 / 100
Maturity
Basic: a single SKILL.md
Security scan
Medium-risk patterns
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • suspicious outbound endpoint
  • mentions secrets in text

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Application security

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.