zeroclaw
Warn
Audited by Socket on Mar 16, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
The skill is broadly consistent with its stated purpose as an autonomous AI infrastructure guide, so it does not show clear malicious misalignment. However, it enables a high-risk runtime: persistent background service, multi-channel control, provider credential use, arbitrary custom endpoints, and a documented no-approval autonomy mode. Overall this looks purpose-aligned but security-sensitive rather than benign-by-default.
Confidence: 82%Severity: 76%
Audit Metadata