monitor-and-review-ai-employee-work
Warn
Audited by Socket on Oct 30, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The task-monitoring and approval capabilities fit the stated purpose, and no direct exfiltration or hidden execution is shown. The main concern is install/execution trust: the skill relies on a separate skill plus an external dozaldevs CLI whose public distribution and release provenance were not verifiably established, creating a high supply-chain/transitive-trust risk despite otherwise coherent behavior.
Confidence: 87%Severity: 74%
Audit Metadata