explain-codebase
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code and documentation, creating a surface for indirect prompt injection via embedded instructions.
- Ingestion points: File reading and repository search across the codebase as described in SKILL.md.
- Boundary markers: The skill instructions emphasize a 'read-only' boundary and focusing on 'observed behavior' before judging the code.
- Capability inventory: No write or network capabilities are included; the tool is restricted to read-only analysis.
- Sanitization: No sanitization or escaping mechanisms for the analyzed code content are defined.
- [NO_CODE]: This skill does not contain any executable scripts, binaries, or automated workflows, which significantly reduces the potential attack surface.
Audit Metadata