prd-writing
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information about product features and problems to generate structured documentation. This represents a standard surface for indirect prompt injection if the user input contains malicious instructions.
- Ingestion points: User-provided product descriptions or feature requests processed by the guidelines in SKILL.md.
- Boundary markers: The skill provides a rigid output structure (Problem, Goals, etc.) which acts as an implicit boundary, but does not explicitly instruct the agent to ignore instructions embedded in the user data.
- Capability inventory: The skill is text-based and does not utilize any tools for network access, file writing, or command execution.
- Sanitization: None detected for user-provided text.
- [SAFE]: The skill includes a reference to the author's public repository on GitHub (github.com/assimovt/productskills) for informational purposes.
Audit Metadata