run-skill
Warn
Audited by Socket on Jul 11, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the stated purpose matches the capability, but the skill materially expands trust by fetching and executing arbitrary remote skills from GitHub/skills.sh. The main risk is transitive remote-instruction execution and prompt-injection style control transfer, not confirmed malware.
Confidence: 86%Severity: 72%
Audit Metadata