code-review

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly fetches PR diffs from GitHub using mcp__github__get_pull_request and mcp__github__get_pull_request_diff and feeds those user-generated PR/diff contents into the code-reviewer agent to read and act on, exposing the agent to untrusted third-party instructions.