context-hub

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and consume live third-party API/SDK documentation using chub (e.g., "chub search <...>" and "chub get --lang py" in SKILL.md, with a fallback to fetching official docs via /browse), and then to implement code strictly from those fetched docs—meaning untrusted, user-generated or public web content would be read and could directly influence actions.