pr-review

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires inspecting third-party packages and their sources (e.g., "node_modules" inspection, running npm view / checking npm registry metadata, and reviewing CocoaPods/Android third-party sources), which causes the agent to fetch and read untrusted public package code/metadata as part of the review workflow.