developer

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

• Third-party content exposure detected (high risk: 0.90). The skill clearly fetches and processes untrusted, user-generated content from public GitHub repositories (e.g., remote_fetch.go / downloadFileFromGitHub, include_expander.go recursive include resolution, and the Go Fan workflow writing to scratchpad/mods/) as part of its compile/analysis workflows, so third-party content can influence compilation and agent behavior.