clj-skill-eval

Warn

Audited by Socket on Sep 15, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS. The skill’s core evaluation purpose is coherent, and its tool/dependency choices are mostly standard for Clojure workflows. However, it explicitly directs the agent to bypass Claude Code permission checks with --dangerously-skip-permissions, which is a significant safety-control circumvention unrelated to measuring skill quality and elevates the overall risk.

Confidence: 90%Severity: 74%
Audit Metadata
Analyzed At
Sep 15, 2026, 11:38 AM
Package URL
pkg:socket/skills-sh/humorless%2Fclj-native-agent%2Fclj-skill-eval%2F@f2df3e2a16c269e2c6273c6a242f7cdcec3210b55733141d21c427501d5958e6
Security Audit — socket — clj-skill-eval