agent-best-practices

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 use "web search" and browser/curl tools to re-read documentation and seek help (see "Pivot Strategies" and "Visual/Web Verification"), which requires fetching and interpreting open/public web content that could contain untrusted, user-generated instructions.