write-product-spec
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input to generate technical documentation, which serves as a potential surface for indirect injection if the resulting specifications are later processed by other automated agents.
- Ingestion points: The skill gathers feature context and summaries via user prompts and the
ask_user_questionfunction inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or
Audit Metadata