when-reviewing-pull-request-orchestrate-comprehensive-code-revie

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

• Third-party content exposure detected (high risk: 0.90). The skill directly fetches and inspects GitHub pull request metadata and changed files via commands like gh pr view and reads PR descriptions/code/comments (arbitrary user-authored content on GitHub), which the agents are expected to read and interpret—exposing the agent to untrusted third-party input.