langfuse-traces

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

• Third-party content exposure detected (high risk: 0.90). The skill's query script (scripts/query.sh) calls the Langfuse API (default LANGFUSE_BASE_URL=https://cloud.langfuse.com) to fetch traces and observations—which include LLM prompts/responses and other user-generated trace data that the agent is intended to read and could materially influence subsequent analysis or actions.