configure-claude-plugins
Warn
Audited by Socket on Apr 21, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill's stated purpose matches its behavior, but it materially expands trust by configuring a third-party plugin marketplace inside write-capable GitHub Actions. The main risks are transitive plugin installation, untrusted comment/PR-triggered agent execution, and broad repo permissions in CI rather than clear evidence of malware.
Confidence: 83%Severity: 76%
Audit Metadata