agent-carnet
Warn
Audited by Socket on May 13, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
The skill’s stated purpose and described data flows are coherent for a local note manager, with no signs of credential harvesting, network exfiltration, or covert behavior. The main risk is install/execution trust: it relies on an external `agent-carnet` binary whose source and publisher cannot be verified from the provided evidence, so the skill is suspicious on supply-chain grounds rather than malicious in function.
Confidence: 82%Severity: 70%
Audit Metadata