codex

Fail

Audited by Runlayer on Feb 26, 2026

Risk Level: HIGH
Scan Summary
Max Score
93%
Files
2
Flagged
2
Chunks
2
Flagged Files (2)
codex/README.mdHIGH
92.6%

Malicious tool definition detected

## Installation Download this repo and store the skill in ~/.claude/skills/codex ``` git clone --depth 1 git@github.com:skills-directory/skill-codex.git /tmp/skills-temp && \ mkdir -p ~/.claude/skills && \ cp -r /tmp/skills-temp/ ~/.claude/skills/codex && \ rm -rf /tmp/skills-temp ``` ## Usage ### Important: Thinking Tokens By default, this skill suppresses thinking tokens (stderr output) using `2>/dev/null` to avoid bloating Claude Code's context window.

codex/SKILL.mdMEDIUM
80.3%

Malicious tool definition detected

Audit Metadata
Max File Score
93%
Classification
KNOWN_SERVER_ALL_UNKNOWN
Files Scanned
2
Files Flagged
2
Chunks Analyzed
2
Analyzed
Feb 26, 2026, 05:28 PM
Security Audit — runlayer — codex