assisted-learning

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

• Third-party content exposure detected (high risk: 1.00). SKILL.md's "Step 2: Research First" explicitly requires using context7 and WebSearch to fetch live documentation and community/best-practice content from the public web, which the agent must read and synthesize into recommendations, exposing it to untrusted third‑party input that could carry indirect prompt injection.