recipe-define
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from local files, which presents a potential injection surface if those files contain malicious instructions.
- Ingestion points: Step 1 in
SKILL.mdreads Opportunity and hypothesis files into the agent context for risk assessment and drafting. - Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded prompts within the ingested files.
- Capability inventory: The skill is capable of writing generated content to the
docs/prd/directory on the local filesystem. - Sanitization: No specific sanitization or validation of the input content is described before it is processed into the PRD.
- [SAFE]: The skill operates entirely within the local filesystem for its intended purpose of document management. It includes a human-in-the-loop confirmation step before writing files, and it does not contain any evidence of obfuscation, remote code execution, or credential theft.
Audit Metadata