tasks
Warn
Audited by Socket on Nov 8, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
The skill’s record-planning capabilities and review gates align with its stated purpose, with no evident credential harvesting, exfiltration, or autonomous execution. However, it requires two CLI tools without establishing the provenance of both; under the unverifiable-dependency rule, this warrants a high security-risk score. The supplied evidence does not establish malicious intent.
Confidence: 82%Severity: 70%
Audit Metadata