prd-generation
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill does not contain any executable code, obfuscated content, or unauthorized network operations. The instructions in
SKILL.mdand the provided templates are purely descriptive and facilitate structured document creation.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input and writes it to a file (design/05-prd.md), which constitutes an attack surface for indirect prompt injection. This is, however, the primary purpose of the skill and is handled safely within the scope of document generation.\n - Ingestion points: Project descriptions, user requirements, and upstream design artifacts provided by the user as described in
SKILL.md.\n - Boundary markers: The skill uses markdown headers to structure output but lacks specific instructions to ignore malicious directives embedded in the input data.\n
- Capability inventory: The skill uses a
Writetool to save output to a pre-defined path on the local filesystem.\n - Sanitization: No explicit sanitization or validation of the input data is performed before it is formatted into the final PRD.
Audit Metadata