create-plan
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill scans untrusted project files (README.md, documentation) to build context, creating an opportunity for indirect prompt injection where malicious instructions in these files influence the agent's output.
- Ingestion points: SKILL.md Workflow Step 1 (reading README.md, docs, and project files).
- Boundary markers: Absent.
- Capability inventory: The skill mandates a read-only workflow, although the output is a plan for future actions.
- Sanitization: Absent.
Audit Metadata