authentication

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

• Third-party content exposure detected (high risk: 0.80). SKILL.md explicitly instructs fetching external markdown via curl from public URLs (e.g., https://fullstackrecipes.com/api/recipes/...) that the agent is expected to read and follow as prerequisite workflow steps, so untrusted third‑party page content could influence actions.