forum-answer-to-video

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

• Third-party content exposure detected (high risk: 0.85). The required workflow ingests the “forum question” and “answer text” provided by the user (outsider-authored forum content) and uses it to draft the script and narration, so that free text becomes LLM context via the user-supplied thread text/answer.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires connecting to Clueso MCP at runtime using the connector URL https://connect.clueso.io/mcp so the assistant can call Clueso tools (i.e., execute remote actions), making this an external runtime dependency that can execute remote code.