codex-cli-task
What this skill does
This skill is a tool for running OpenAI Codex CLI tasks in the background and delivering results to OpenClaw agents. It is designed for complex tasks like coding, research, and analysis, and is not in
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=codex-cli-taskAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
run-task.sh
The script uses the 'codex --search exec' command with the '--dangerously-bypass-approvals-and-sandbox' flag, which could allow the execution of arbitrary code and potentially exfiltrate data.Excessive Agency
Excessive Agency via local-llm-review
run-task.sh
The script runs Codex CLI tasks in the background with no user interaction, which could lead to excessive agency and unintended consequences.Badge
Add the Anomity scan badge for codex-cli-task 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-cli-task? Report an issue or request a rescan.
