github-presence

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill does not contain any malicious code, obfuscation, or direct prompt injection attempts. Its behavior is consistent with its stated purpose of providing GitHub optimization advice.
  • [CREDENTIALS_UNSAFE]: The skill follows security best practices by recommending the use of GitHub Secrets syntax (e.g., ${{ secrets.METRICS_TOKEN }}) in its workflow templates rather than hardcoding sensitive information.
  • [EXTERNAL_DOWNLOADS]: All external references and templates point to well-known and trusted services such as Shields.io, Vercel, and official GitHub Actions (e.g., actions/checkout), which are documented neutrally as standard project dependencies.
  • [PROMPT_INJECTION]: The skill presents a low risk of indirect prompt injection during the 'README Audit' task, where it may process untrusted content from external repositories.
  • Ingestion points: External repository README files and issue/PR descriptions.
  • Boundary markers: None explicitly defined in the templates.
  • Capability inventory: The skill provides instructions and text-based suggestions but does not include scripts that execute system commands or perform network operations.
  • Sanitization: None specified for input processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 08:38 PM