workflow-skill-creator

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). This workflow explicitly invokes a "skill-researcher" in Step 1 (Research Domain & Patterns) that performs Web Search, GitHub, and public documentation research—i.e., it ingests open/public user-generated third‑party content which the agent is expected to read and synthesize, exposing it to indirect prompt injection risk.