product-design
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external 'product evidence and implementation', which acts as a surface for indirect instructions hidden in documentation or source code.
- Ingestion points: The skill reads product evidence and current implementation files during the diagnosis phase (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore embedded commands within the external evidence.
- Capability inventory: The agent is authorized to implement workflow changes, execute relevant tests, and perform browser inspections (SKILL.md).
- Sanitization: There is no mention of input validation, escaping, or content filtering for the analyzed product materials.
Audit Metadata