skills/agent-sh/agentsys/repo-intel/Gen Agent Trust Hub

repo-intel

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill definition does not contain any detected malicious patterns, obfuscation, or unauthorized access attempts.
  • [PROMPT_INJECTION]: The skill processes untrusted repository data including git history and AST symbols, which is a surface for indirect prompt injection. 1. Ingestion points: Git history, AST symbols, and project metadata (referenced in SKILL.md). 2. Boundary markers: Not explicitly implemented in the prompt instructions. 3. Capability inventory: Reads git history and writes to platform state directories (.claude, .opencode, .codex). 4. Sanitization: No explicit sanitization or validation of the repository content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 03:23 PM