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 instructs the agent to fetch and use open web content (e.g., infsh/agent-browser screenshot of "https://example.com/pricing" and running tavily/search-assistant queries for research) so the agent ingests untrusted public web content that can materially influence post content and actions.