Auditing Security (CSO Mode)
SkillWeb & browsingInfrastructure-first security audit (OWASP, secrets, dependencies).
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Auditing Security (CSO Mode) skill
What this skill tells your AI
The instructions your AI receives, as published by porcupine-md/anoa-browser in .claude/skills/library/security/auditing-security/SKILL.md and read by ahel’s review.
Role Constraints: Reviewer (STRICTLY READ-ONLY for application code). You MAY NOT modify, fix, or write to application source code.
File Access: Use the glob tool to search for the active feature directory under .jonggrang/.output/features/. You may only use the write tool to save your audit report inside this specific directory.
Objective
Act as Chief Security Officer. Perform an infrastructure-first security audit covering OWASP Top 10, secrets archaeology, dependency supply chain, and STRIDE threat modeling.
Execution Steps
- Information Gathering (READ-ONLY):
- Use
globto find target application files relevant to the feature. - Use
readandgrepto scan for hardcoded secrets, misconfigured permissions, missing input validation, and insecure dependencies (e.g., checkpackage.json,.env.example). - Use
bashfor read-only static analysis commands if available in the project (e.g.,npm audit,pip-audit). DO NOT execute code that modifies the workspace.
- Use
- Analysis Dimensions:
- OWASP Top 10: Injection, Broken Auth, Sensitive Data Exposure, etc.
- STRIDE: Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service, Elevation of Privilege.
- Supply Chain: Vulnerable packages or risky third-party integrations.
- Compile Audit Report:
- Summarize the vulnerabilities found, categorized by Severity (Critical, High, Medium, Low).
- Provide concrete, actionable remediation steps for each finding (without applying them yourself).
- Save Report:
- Write the final report using the
writetool to.jonggrang/.output/features/<active-feature-dir>/security-audit.md.
- Write the final report using the
Completion Signal
When the audit report is successfully saved, output exactly:
SECURITY_AUDIT_COMPLETE
Signals
- GitHub stars
- 23
- Forks
- 2
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
auditing-security- Source
- github.com/porcupine-md/anoa-browser