gh-workflow

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to inspect and act on GitHub repository workflow files (e.g., checking .github/workflows/ and using gh on github.com), which are user-generated public content that the agent must read and interpret to decide and run actions, so untrusted third-party content can influence behavior.