coding-agent
Warn
Audited by Socket on May 15, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s purpose matches its coding-agent capabilities and the install sources are official, so this is not malware-like. However, it grants external coding CLIs broad autonomy over local repos and GitHub actions, explicitly recommends reduced-permission modes, and processes untrusted PR/repo content with write/exec access, creating high operational risk.
Confidence: 90%Severity: 72%
Audit Metadata