codex-config

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly references fetching public third-party content — e.g., the built-in "$skill-installer" which downloads skills from GitHub and the "--search" flag that "Enable[s] web search tool" — indicating the agent will fetch and read untrusted public web content as part of its workflow.