codex-first
Claude Code-only work routing: delegate implementation, fixing, exploratory subagents, rebasing, and PR merging/landing to Codex CLI while Claude specifies, decides, reviews, and verifies. Direct hands-on delegation requires ANTHROPIC_BASE_URL to be unset or neither loopback nor gorillaclaw.sheep-coho.ts.net. Codex-backed autoreview is always allowed and preferred, independent of environment.
61
72%
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
3 findings: 2 critical severity, 1 medium 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
Direct link to a remote install.sh piped to sh on chatgpt.com is a high-risk pattern (remote executable script run without verification) and is not the official OpenAI/openai.com download flow.
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 document contains multiple explicit instructions that bypass sandboxing/approvals, enable arbitrary command execution, suppress/log-hide execution details, and instruct installing remote scripts — patterns that present high risk for backdoor/RCE and supply-chain abuse.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill explicitly tells the agent to run the Codex CLI with "--yolo" and even to resume with "--dangerously-bypass-approvals-and-sandbox", encouraging arbitrary command execution and bypassing sandbox/approval mechanisms that can modify the machine state.
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 an install-time command that fetches and pipes remote code to a shell (curl -fsSL https://chatgpt.com/codex/install.sh | sh), which executes remote code and can control the installed CLI used at runtime.
- Repository
- steipete/agent-scripts
- Commit
bb36883
- 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.