production-compass
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data provided by the user during the 'decision-tree-interview' and 'requested destination' phases to guide its production mapping.
- Ingestion points: User-supplied project destinations and inputs provided during the breadth-first interview process (SKILL.md).
- Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions to prevent the agent from following commands embedded within the creative project descriptions.
- Capability inventory: The skill utilizes file system write capabilities to create and update 'decision_map.json', 'decision_map.md', and 'creative_decisions.jsonl', and performs 'factual research' which may involve tool-assisted web searches.
- Sanitization: No sanitization or validation logic is specified for the content processed during the decision-making frontier graduation.
Audit Metadata