Deep security audit of code, dependencies, and infrastructure. Checks OWASP Top 10, authentication, authorization, data protection, and dependency vulnerabilities. Use before releases or after significant changes.
From agent-triforcenpx claudepluginhub artemiopadilla/agent-triforce --plugin agent-triforceThis skill uses the workspace's default tool permissions.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Implements structured self-debugging workflow for AI agent failures: capture errors, diagnose patterns like loops or context overflow, apply contained recoveries, and generate introspection reports.
Perform a security audit on: $ARGUMENTS
If no specific scope is provided, audit the entire src/ directory.
Follow these steps:
SIGN IN:
AUDIT:
npm audit / pip auditIf any Critical finding: invoke the NON-NORMAL: Critical Vulnerability Response checklist from your agent file.
⏸️ TIME OUT — Run Verification Checklists (DO-CONFIRM): 7. Run through the Security Verification checklist from your agent file 8. Run through the Quality Verification checklist from your agent file 9. Issue verdict based on findings
SIGN OUT:
10. Write report to docs/reviews/security-audit-{date}.md
11. Write the Findings Handoff-to-Forja using the communication checklist
12. Run the SIGN OUT checklist from your agent file