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 is a legitimate local monthly-review workflow with no malicious intent, but the TypeScript helper hardcodes a fabricated daily-planning rate (80%) that the code's own comment says should come from real data, so the output presents mock data as a measured metric.
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.