devloop
Warn
Audited by Socket on Aug 24, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill's automation and local code-modification behavior mostly fit its stated purpose, but it materially increases risk through unattended execution, scheduled control loops, and transitive installation of other skills from GitHub. I found no clear credential theft or exfiltration, so this is better classified as high-risk automation and trust expansion rather than confirmed malware.
Confidence: 86%Severity: 76%
Audit Metadata