gitlab-mr-review

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches GitLab merge request metadata, diffs, and discussions (Steps 1 and 4 of SKILL.md), which are user-generated/untrusted third-party contents that the agent must read and use to form findings and take actions (e.g., posting comments), so these sources could carry instructions that influence the agent's decisions.