twitter-thread-creation

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly directs the agent to fetch and use open web content—e.g., "belt app run infsh/agent-browser" with a URL (https://example.com/pricing) and "belt app run tavily/search-assistant" for web research—so untrusted public webpages/search results are ingested and used to craft posts/evidence, which could materially influence agent actions.