autopilot
Warn
Audited by Socket on May 10, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s behavior is broadly aligned with an 'autopilot developer workflow,' but its trust footprint is high. The main concerns are extensive autonomous real-world actions without intermediate approval, transitive execution through other skills, and reliance on an unverifiable `af` CLI for Jira/Jenkins operations. No clear evidence of malware or credential theft was shown, but the overall security risk is high.
Confidence: 86%Severity: 81%
Audit Metadata