codex

Warn

Audited by Socket on Aug 28, 2026

1 alert found:

Anomaly
AnomalyLOW
SKILL.md

Mostly coherent coding-agent skill using the official OpenAI Codex CLI and standard git/GitHub workflows. Main risk is not malware but powerful autonomous developer actions, including unsandboxed Codex execution, remote repo/PR processing, and public posting/push operations; use only with tight repo scope and explicit approval for commits, pushes, and comments.

Confidence: 90%Severity: 66%
Audit Metadata
Analyzed At
Aug 28, 2026, 12:48 PM
Package URL
pkg:socket/skills-sh/tt-a1i%2Fhermes-agent%2Fcodex%2F@524d66e24e6c3f4113363ed5d47dc36fc785a8456dad59c92155b24047dccba9
Security Audit — socket — codex