devin-review-init

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 instructs the agent to read and analyze arbitrary repository contents and related GitHub resources (Phase 1: "Explore the Repository" — check package.json, docs, recent PRs/issues) and even shows a CLI that fetches a public PR URL (npx devin-review https://github.com/owner/repo/pull/123), so it ingests untrusted, user-generated third‑party content that can materially alter generated review/agent files.