docs-agent-audit

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly asks for a user-provided docs site URL and instructs the agent to WebFetch that site (fetching /llms.txt, /llms-full.txt, robots.txt, sitemap.xml, and root/docs pages) and then read/interpret those public pages to drive audit findings and next actions, so untrusted third-party content can influence behavior.