ce-review

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

• Third-party content exposure detected (high risk: 0.70). The skill's workflow explicitly says it will "resolve PR/branch/diff, fetch metadata, collect signals, read linked artifacts" (Phase 1 in SKILL.md) and to "escalate to current external docs" such as official framework docs or Context7 when needed (references/review-modes.md), meaning the agent will fetch and interpret user-/third-party-generated content (PRs, repo-linked artifacts, external docs) that can materially influence review decisions.