long-horizon

Warn

Audited by Socket on Aug 29, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS: the skill is internally coherent as an autonomous orchestration skill, but its footprint is high-risk because it enables hours-long unattended action and transitive reliance on other skills. Main concerns are autonomous git/PR actions and inherited trust from loaded companion skills, not malware or credential theft.

Confidence: 86%Severity: 74%
Audit Metadata
Analyzed At
Aug 29, 2026, 09:35 AM
Package URL
pkg:socket/skills-sh/keli-wen%2Fdev-skills%2Flong-horizon%2F@30d2c8ec974b92e3c5e799f2bdd68be3f818c85c12d92a6f3ce3ab1d3f4a1bba
Security Audit — socket — long-horizon