oss-maintainer

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No security issues were detected. The skill provides instructional guidance for project maintenance using standard tools like the GitHub CLI and testing frameworks.
  • [PROMPT_INJECTION]: The skill inherently processes untrusted data from external contribu t o r s (issues, PRs), which is a common surface for indirect prompt injection. 1. Ingestion points: Incoming issues and community PRs as described in SKIL L.md. 2. Boundary markers: None explicitly defined; the instructions do not use specific delimiters for external data. 3. Capability inventory: Use of GitHub CLI (gh) and Python testing (pytest) for repository management and testing. 4. Sanitization: Relies on explicit instructions for manual, line-by-line code review and indepen d e n t verification of claims.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 09:16 PM
Security Audit — agent-trust-hub — oss-maintainer