pack-validate
Warn
Audited by Socket on May 7, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s purpose is coherent and scope is narrow, but it asks the agent to execute an unverifiable repo-local shell script with no public provenance or release evidence. No credential theft or exfiltration is visible, so this is better classified as a supply-chain trust risk than malware.
Confidence: 84%Severity: 72%
Audit Metadata