get-api-docs

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to run "chub search" and "chub get " to fetch and "Read the fetched content and use it to write accurate code" from third-party API docs (e.g., openai/chat, stripe/api), so untrusted external documentation can directly influence tool use and actions.