context-hub

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to run chub search/get (e.g., "chub get --lang py") to fetch up-to-date third‑party API/SDK documentation such as "openai/chat" or "stripe/api" and then to read and implement from those fetched docs, which means the agent will ingest and act on external, public third‑party content that could contain adversarial instructions.