start
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill manages project documentation by reading from and writing to specific paths like
specs/requirements/prd.md. It does not attempt to access sensitive system files, credentials, or environment variables. - [COMMAND_EXECUTION]: No evidence of shell command execution, subprocess spawning, or privilege escalation was found. The skill uses platform-native functions for document generation.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied project briefs and interview responses to populate the PRD. While this data ingestion represents a potential surface for indirect prompt injection, the skill incorporates structured sections and a 'contract' reference to maintain document integrity. The resulting document is intended for project planning rather than direct execution by the agent.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute external code or dependencies. It relies on internal references and user input.
Audit Metadata