developing-features
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external codebase content which represents an attack surface for indirect prompt injection.
- Ingestion points: Phase 2 (Codebase Exploration) instructs the agent to read 5-10 key files per explorer agent to build deep context.
- Boundary markers: The skill lacks explicit instructions to treat codebase content as data rather than instructions, or to use delimiters when processing these files.
- Capability inventory: The skill has the capability to write and modify files during Phase 5 (Implementation) based on the context gathered.
- Sanitization: There are no explicit sanitization or validation steps mentioned for the content read from the codebase.
Audit Metadata