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
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:35 AM