writing-agents

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs in "Step 1: Research Domain Best Practices" to "Use WebSearch to find domain-specific guidance" and to "Incorporate findings" into agent definitions, which requires fetching and interpreting untrusted public web content that can influence agent behavior.