Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill's core purpose is a benign quarterly review, but it repeatedly routes the user's personal review data through an unpinned third-party package (`npx claude-flow@alpha hooks ...`) whose behavior is never explained, so the user would not expect their data to leave the local files.
kmondlane/ExoMind
8794d26
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.