gate
Warn
Audited by Socket on May 4, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: The skill’s purpose mostly matches its capabilities, but it relies on an opaque plugin-bundled CLI whose provenance is not independently verifiable from the provided evidence. The bounded self-healing loop is operationally plausible, yet it grants autonomous code-editing and command execution based on untrusted command output, making the overall security risk high even without clear evidence of credential theft or exfiltration.
Confidence: 83%Severity: 74%
Audit Metadata