codex-first
Claude Code work routing: delegate implementation, fixing, exploratory subagents, rebasing, and PR merging/landing to Codex CLI while the parent specifies, decides, reviews, and verifies. Load a private codex-next policy first when available; otherwise use the native-Claude model gate. Codex-backed autoreview is always allowed and preferred.
66
80%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./skills/codex-first/SKILL.mdSecurity
2 findings: 2 critical severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
Piping a shell script straight from a hosted URL (https://chatgpt.com/codex/install.sh) is high-risk — it's a direct .sh installer that could execute arbitrary code, and remote install scripts should only be used from fully trusted, verifiable vendor sources after inspection.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
The skill contains explicit instructions to bypass sandboxing/approval controls (--yolo, --approve-for-me, --dangerously-bypass-approvals-and-sandbox) and to fetch/run a remote install script via curl|sh, which together create high-risk avenues for remote code execution and supply-chain compromise.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill includes a runtime installation command that fetches and executes remote code via curl -fsSL https://chatgpt.com/codex/install.sh | sh, which if run would execute external code and is presented as an installation/runtime step.
- Repository
- steipete/agent-scripts
- Commit
efa3b2f
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.