ml-foundation-potentials
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of purely documentation and instructional content regarding the selection of various foundation models for machine learning simulations. It does not contain any executable scripts or hidden logic.
- [COMMAND_EXECUTION]: The file provides documentation for expected MCP tool calls, such as
mcp_base_search_model_registryandregister_model. These are demonstrated as standard tool interactions within a controlled environment and do not constitute arbitrary or dangerous command execution. - [EXTERNAL_DOWNLOADS]: The skill references various machine learning models (CHGNet, FAIRCHEM, MACE) and includes a link to the author's official GitHub profile. No automated downloads or remote script executions (e.g., via curl or wget) were detected.
- [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found in the text or metadata.
Audit Metadata