chatti

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly directs the agent to connect to Chatti and to issue Membrane actions or proxy requests against the Chatti API (see "Working with Chatti" and "Proxy requests" in SKILL.md), which will ingest user-generated chat/message content from a third-party messaging platform and therefore could carry indirect prompt-injection instructions.