plan-issue-gemini
Warn
Audited by Socket on Apr 11, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill's purpose is plausible, but its implementation relies on executing an unpinned third-party npm package via `bunx` with broad Bash permission. That creates a meaningful supply-chain and transitive-trust risk even though there is no direct evidence of credential theft or overtly malicious behavior in the snippet.
Confidence: 84%Severity: 72%
Audit Metadata