create-plan
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external documents to populate plans and code snippets, creating a potential surface for indirect prompt injection. However, this is a standard workflow surface and the risk is mitigated by explicit human review checkpoints.\n
- Ingestion points: Reads project documents from
thoughts/shared/directories.\n - Boundary markers: None explicitly defined in instructions.\n
- Capability inventory: Local file system write access and spawning of helper agents.\n
- Sanitization: Mandatory human approval steps are integrated into the workflow.
Audit Metadata