zod

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly tells the agent to "Fetch live documentation for up-to-date details" and points to the public docs at https://zod.dev/llms.txt, so the agent would fetch and interpret content from an open third-party website that could influence its behavior.