geo-audit

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 explicitly invokes external documentation via Context7 MCP (Step 1) and performs spot-checks of linked/public URLs from llms.txt and other web docs (Category 1 checks), meaning the agent will fetch and interpret untrusted public web content that can materially influence audit decisions.