security-reviewer

Warn

Audited by Socket on Mar 13, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS. The skill is internally aligned with its stated purpose and shows no hidden install chain, credential harvesting, or exfiltration path. However, it grants an AI agent Bash-enabled offensive security capabilities including penetration testing and reconnaissance, which is inherently high risk even with stated authorization constraints.

Confidence: 90%Severity: 74%
Audit Metadata
Analyzed At
Mar 13, 2026, 06:28 AM
Package URL
pkg:socket/skills-sh/sundial-org%2Fawesome-openclaw-skills%2Fsecurity-reviewer%2F@1b605b432d83dd658276e45c0654ffbb2f5b98f1