The Agent Skills Directory

[SAFE] (SAFE): No security threats identified. The skill provides documentation on knowledge graphs, molecular property prediction, and protein modeling using standard academic datasets and models.
[Prompt Injection] (SAFE): No instructions to override agent behavior or bypass safety filters were found.
[Data Exposure & Exfiltration] (SAFE): No access to sensitive credentials or system files. Data paths used in snippets (~/kg-datasets/, ~/molecule-datasets/) are standard for local storage of research data.
[Remote Code Execution] (SAFE): No remote script downloads or dynamic code execution patterns detected. The code snippets are static examples for training and evaluation of ML models.

torchdrug