sc-hypothesize

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md Induction phase explicitly requires the agent to "collect actual evidence" by running searches and "check docs," and the Evidence Quality section names blog posts and Stack Overflow as sources, so the agent is expected to fetch and interpret untrusted public web/user-generated content that can influence decisions.