claude-code-restored-runtime
Warn
Audited by Socket on May 16, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill's functionality mostly matches its purpose, but it asks users to clone and run an unofficial reconstructed Claude-like runtime from a personal repo and feed it GitHub credentials. The main risk is supply-chain trust and credential forwarding into non-upstream code, not confirmed malware or obvious exfiltration.
Confidence: 86%Severity: 72%
Audit Metadata