ratel-langfuse-analyze

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is ingested when the skill fetches full trace bodies via the Langfuse MCP server (Step 4: langfuse_get_trace(... include_input_output=true ...)), where the trace input/output transcripts are authored by the customer’s users/agents rather than the operating user.