tapd

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

• Third-party content exposure detected (high risk: 0.70). SKILL.md describes a runtime workflow where the agent executes scripts/tapd.py get_stories_or_tasks and then parses the returned description/images fields (including downloading via download_url), which originates from TAPD content authored by other users (outsider) and is ingested as readable text/JSON into the LLM context.