skills/howells/arc/letsgo/Gen Agent Trust Hub

letsgo

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a structured workflow for auditing projects and preparing them for production. All shell commands (pnpm, vercel, git) are used within their standard contexts for building, testing, and deploying web applications.
  • [PROMPT_INJECTION]: The skill scans project files (e.g., package.json, configuration files) to tailor its checklist. While this creates a surface for indirect prompt injection, it is the primary intended function of the skill and no malicious redirection patterns were found.
  • Ingestion points: Step 1 project detection scans the codebase for frameworks, auth libraries, and configuration signals.
  • Boundary markers: Absent; the skill relies on the agent's natural language processing to interpret the scan results.
  • Capability inventory: Can execute build, test, and deployment commands (pnpm build, pnpm test, vercel --prod, git push).
  • Sanitization: Not applicable; the skill generates a checklist for human review based on the detected strings.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 04:39 PM
Security Audit — agent-trust-hub — letsgo