foldrun@26.17.0
Agents are just folders. Write them, check them, run them — on your machine.
AI security review
scanned · by lpm-firewall-aiThe flagged process execution supports documented, user-invoked CLI features, and model credentials are used for agent runs. The prepare script is conditional and no install-time exfiltration or other concrete attack was found.
Decision evidence
public snapshot- The package exposes a CLI entry point and depends on its own @foldrun/core runtime.