bugfix
Warn
Audited by Socket on Apr 8, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
This skill is mostly coherent with a bug-fixing purpose, but its trust surface is larger than the description suggests: broad local execution rights, reliance on an external hoyeon-cli with no provenance here, and delegation to other skills for implementation/QA. No clear credential theft or exfiltration is shown, so this is better classified as suspicious/high-risk workflow design rather than malicious.
Confidence: 72%Severity: 72%
Audit Metadata