grill-me-quick

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly dispatches subagents that are instructed to use WebSearch/Read/Bash and return external "evidence" (see references/verification.md under "Subagent brief" and "Required output"), meaning it will fetch and interpret public web or other third-party content to verify claims and those results can change decisions or next actions.