product-spec-builder
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes existing document content during its update cycle.
- Ingestion points: In the 'Iteration Mode' defined in
SKILL.md, the skill is instructed to read the existingProduct-Spec.mdfile. - Boundary markers: The skill does not define clear delimiters or specific instructions to isolate the data within
Product-Spec.mdfrom the agent's operational instructions. - Capability inventory: The skill maintains the ability to write to and modify files in the project workspace, specifically
Product-Spec.mdandProduct-Spec-CHANGELOG.md. - Sanitization: There is no evidence of content validation or escaping of the data ingested from existing files before it is processed by the agent.
Audit Metadata