pr-antipattern-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 and parses public PR/commit diffs and PR title/body from external GitHub/GitLab URLs (Step 1: "fetch <URL>.diff with the available browser/web tool or curl -L" and "Always scan the PR title and body" in references/diff-checks.md), which are untrusted, user-generated third-party content that the agent reads and uses to make review decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches remote PR diffs at runtime (e.g., github.com///pull/ and gitlab.com/.../merge_requests/ / <URL>.diff via curl -L) and injects that fetched diff text into the agent's review context, so external content can directly control prompts.