ai-pr-review

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to fetch PR diffs, read source files, and fetch linked issue acceptance criteria from GitHub (via the gh CLI) — all user-generated/untrusted third-party content that the agent reads and uses to decide reviews and apply fixes (e.g., "Fetch PR diff and metadata", "Fetch issue acceptance criteria" in Review Workflow and Usage Instructions).