review-work

SUSPICIOUS: the skill’s review purpose broadly matches its capabilities, but its footprint is expansive for a review helper. The main risks are autonomous multi-agent execution, extensive repo/context collection, and especially ingestion of untrusted GitHub/Slack/Notion content by agents that can run commands and access files. No confirmed malware or overt credential theft is present, but the skill is medium-high risk and should be treated carefully in sensitive environments.