gitlab-address-comments

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

• Third-party content exposure detected (high risk: 0.90). The skill's scripts/fetch_comments.py calls glab api to fetch GitLab merge request discussions (user-generated MR comments) and the skill then loads and interprets those discussion JSON files (e.g., /tmp/*_mr_open_discussions.json) to summarize and act on review threads, exposing the agent to untrusted third-party content from GitLab.