paw-mkt-cro

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly depends on and instructs using the agent-browser for "live URL audit" (see Dependencies and the Response Protocol step 1 in SKILL.md), meaning the agent will fetch and interpret public third-party pages as the working source of truth for audits and recommendations, exposing it to untrusted web content that could contain indirect prompt injection.