repo-research-analyst
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious instructions, obfuscation, or unauthorized command executions were found. The skill operates within the expected boundaries of a repository analysis tool.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it is designed to read and process untrusted repository content (documentation, issues, templates, and source code). This is an inherent risk given the skill's purpose. Evidence: (1) Ingestion points: repository files accessed via read, grep, glob, and ast-grep tools; (2) Boundary markers: no explicit markers or 'ignore' instructions are provided for repo content; (3) Capability inventory: limited to file-reading and searching; (4) Sanitization: no content sanitization is described.
Audit Metadata