intent-discovery
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the codebase during its initial survey phase, which could contain malicious instructions intended to manipulate the design outcome or influence the agent's logic.
- Ingestion points: Reads relevant files, documentation, and recent commit history (SKILL.md, Step 1).
- Boundary markers: The instructions do not define delimiters or specific warnings to ignore embedded instructions within the files being read.
- Capability inventory: The skill can write files to the 'docs/plans/' directory, perform git commits (SKILL.md, Step 8), and dispatch subagents (SKILL.md, Step 9).
- Sanitization: There is no evidence of content validation or sanitization for the data read from external project files.
Audit Metadata