The Agent Skills Directory

[NO_CODE]: The skill consists entirely of natural language instructions and does not contain any executable scripts, binary files, or package dependencies.
[SAFE]: The instructions include strong safety constraints and ethical boundaries, specifically prohibiting the agent from diagnosing conditions or recommending medical treatments. It also provides clear escalation paths for urgent medical concerns.
[DATA_EXPOSURE]: No mechanisms for data exfiltration or credential harvesting were identified. The skill processes user-provided data within the conversation context without external transmission.
[REMOTE_CODE_EXECUTION]: There are no external downloads or remote script execution patterns present.

bloodwork-explainer