codex

Warn

Audited by Socket on Jun 14, 2026

1 alert found:

Anomaly
AnomalyLOW
SKILL.md

SUSPICIOUS: the Codex integration itself is mostly coherent and uses official OpenAI distribution, but the skill's actual footprint is broader than its stated purpose. It mixes a reasonable external AI review wrapper with local helper-script execution, transitive skill invocation, telemetry/logging, outbound project-content transfer to Codex, and some autonomous file/git changes outside the core review task.

Confidence: 100%Severity: 60%
Audit Metadata
Analyzed At
Jun 14, 2026, 08:51 AM
Package URL
pkg:socket/skills-sh/charlieviettq%2Fawesome-agent-skill%2Fcodex%2F@b7617408d4aec53f7827a0b1143694c99edb2eccc69c990b002de56576c42311
Security Audit — socket — codex