define-requirement
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources which could contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: The skill reads
AGENTS.md,.agents/PROJECT_CONTEXT.md,.agents/state.json, and the generated PRD file. It also processes user input during the interview. - Boundary markers: Absent. There are no explicit instructions to the agent to treat these files as data only or to ignore embedded directives.
- Capability inventory: The skill has file-read, file-write, and directory exploration capabilities.
- Sanitization: Absent. The skill does not explicitly sanitize the content retrieved from project files or user input before processing.
Audit Metadata