plan-to-tasks
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests and processes user-provided project plans/markdown (the "User provides a project plan/spec" and "Converting markdown plans to JSONL format" statements), which are untrusted third-party/user-generated content that the agent must read and interpret as part of its workflow.
Audit Metadata