recon
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a structural framework for codebase documentation. It does not contain executable code, system commands, or external dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect injection as it is designed to ingest and process untrusted codebase metadata.
- Ingestion points: Target scope, entrypoints, files, and symbols are provided as context to subagents during the Dispatch phase (SKILL.md).
- Boundary markers: The instructions mandate a specific "Canonical Codebase Cartography Format" for all outputs, providing a structured boundary for generated content.
- Capability inventory: The skill is restricted to information synthesis and reporting. It contains an explicit instruction to "Never propose diffs or edit files," significantly reducing the impact of potential injection.
- Sanitization: No specific sanitization or filtering logic is defined for the input metadata.
Audit Metadata