ft-research
Warn
Audited by Socket on Oct 18, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The stated research purpose mostly matches the file-writing workflow, but the skill includes a non-transparent auxiliary mode and requires executing an unverified local shell script from a sibling path. There is no clear credential harvesting or external exfiltration path, but the hidden-to-user behavior plus unverifiable executable dependency make the skill medium-high risk.
Confidence: 81%Severity: 72%
Audit Metadata