coding-agent
Fail
Audited by Socket on Apr 18, 2026
1 alert found:
MalwareMalwareSKILL.md
HIGHMalwareHIGH
SKILL.md
SUSPICIOUS: the skill is purpose-aligned, but it grants broad delegated execution to external coding-agent CLIs, encourages high-autonomy modes, and processes untrusted PR/repo content with write/exec capability. No clear credential theft or malicious exfiltration is present, but the operational risk is medium due to autonomous actions and third-party CLI trust.
Confidence: 80%Severity: 66%
Audit Metadata