code-reviewer

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

• Third-party content exposure detected (high risk: 0.75). The skill ingests outsider-authored free text when the operating user requests a review of a PR/diff (e.g., via gh pr diff <N> or inline pasted diffs), because the diff content is authored by other contributors and is fed into the reviewers’ LLM context as “Diff source” in the runtime review prompts.