x-mastery-mentor

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md (Scene E, Step 2) instructs the agent to browse and scrape https://x.com/{username} (and use browser/DOM tools) to ingest user-generated tweets and metadata, which the agent then analyzes to produce diagnostics and action plans—meeting all criteria for ingesting untrusted third‑party content that can influence tool use and decisions.