Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →miosa-osa/security-auditor
Comprehensive security analysis and vulnerability detection
Passed 15 of 22 test cases with the skill, and 9 of 22 without it.
and 7 more in the full report
6 fixed9 passed either way7 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
After resolving an audit session where React built-in escaping was adopted to fix an XSS vulnerability, how should this self-learning memory entry be saved using the slash command protocol?
| Checked | Without skill | With skill |
|---|---|---|
| Uses the /mem-save command prefix. | Missed | Passed |
| Uses the solution subcategory tag when storing the remediation approach. | Missed | Passed |
The instructions your model reads when the skill loads.
This skill activates when:
.env*, *secret*, *credential*, Dockerfile, *.tf, *security*Identify the security surface and project characteristics.
Actions:
1. Detect project type and languages
2. Identify sensitive file patterns
3. Check for existing security configurations
4. Review .gitignore for security patterns
Run static code analysis for vulnerabilities.
Tools:
- Semgrep: Multi-language SAST
- Bandit: Python-specific security
- ESLint security plugin: JavaScript/TypeScript
- Gosec: Go security
Rulesets:
- p/security-audit
- p/owasp-top-ten
- p/secrets
- p/sql-injection
- p/xss
test cases passed, vs 9 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.