codex-image

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires reading the user's access token from ~/.codex/auth.json and using it verbatim in HTTP requests/headers (and may display it via status), so the LLM must handle and embed secret credential values directly.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This code intentionally impersonates the official Codex CLI and reuses local ChatGPT OAuth credentials (~/.codex/auth.json) to stealthily consume the user's ChatGPT subscription quota for image generation, a deliberate deception/abuse of authentication and service fingerprints that can be used to misuse an account and upload user images to external APIs.