codebase-recon
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from external codebases and documentation.
- Ingestion points: SKILL.md specifies gathering evidence from code, docs, tests, and history.
- Boundary markers: The instructions lack explicit delimiters or guidance to ignore instructions that might be embedded within the analyzed source code or external documentation.
- Capability inventory: The skill relies on the agent's default tools for file reading, searching, and web access.
- Sanitization: There are no defined procedures for sanitizing or validating external content before it enters the agent's context.
- [EXTERNAL_DOWNLOADS]: The skill methodology includes gathering information from external research sites.
- Evidence: SKILL.md lists library documentation, Stack Overflow, and RFCs as evidence sources for investigation.
Audit Metadata