grill-me

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md "How to find answers before asking" section explicitly directs the agent to use WebSearch and WebFetch to verify claims and consult public web/docs, which means the agent will fetch and interpret untrusted third-party content from the open web that can influence its recommendations.