assess-findings

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow mandates a "Web search" for every finding (see SKILL.md Phase 1: "Mandatory for every finding:
• Web search to verify..."), so the agent is expected to fetch and interpret open/public web content that could contain untrusted, user-generated instructions influencing its decisions.