codebase-memory
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of external codebases, which are considered untrusted data sources.
- Ingestion points: Data enters the agent context through tools like
index_repository,search_code,get_code_snippet, andquery_graph. - Boundary markers: The instructions do not define explicit delimiters or warnings to prevent the agent from following instructions that might be embedded in code comments or documentation (e.g., in a README or source file).
- Capability inventory: The skill provides structural traversal, source code access, and complex graph querying capabilities.
- Sanitization: No specific sanitization or filtering logic is described for the content retrieved from the indexed repositories.
Audit Metadata