trace-triage

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow in SKILL.md uses the Progress Observability MCP to fetch outsider-authored trace prompt/tool-argument content via get_observation_details_with_content (for selected span IDs) after identifying a culprit span from observations, making untrusted free text available for the LLM to ingest at runtime.