code-to-pantry
Warn
Audited by Socket on Apr 4, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill's main behavior matches its purpose, but it enables autonomous remote writes to a personal GitHub repo and references execution of GitHub-hosted code via bunx from a mutable repo. This is not confirmed malware and there is no obvious credential theft, but the public push capability and transitive GitHub execution make it a medium-risk skill that should only run with explicit user approval.
Confidence: 84%Severity: 58%
Audit Metadata