codex-skill
What this skill does
This skill is a wrapper or interface for the Codex CLI, designed to automate coding tasks using models like Codex, GPT-5, or GPT-5.1. It provides non-interactive automation for hands-off task executio
github/leoyeai - Security Risk - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=codex-skillAssessments (1)
Security Risk
Security Risk via local-llm-review
SKILL.md
The flag `--dangerously-bypass-approvals-and-sandbox` allows the agent to skip all prompts and operate without sandboxing. This could be used to execute arbitrary code or access sensitive system resouBadge
Add the Anomity scan badge for codex-skill to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of codex-skill? Report an issue or request a rescan.
