image-gen

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill includes examples that pass an API key directly on the command line and writes an API key into a plaintext config (e.g., --api-key ak_你的密钥, export REDFOX_API_KEY=ak_你的密钥, echo '{"api_key":"ak_你的密钥"}'), which implies the LLM would need to handle or output secret values verbatim.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). In assets/imagegen.py the runtime directly ingests the user-provided CLI argument prompt (parsed as args.prompt) and submits it to RedFoxHub via SUBMIT_URL as JSON payload without any internal “select an item” gating, so outsider-authored free text is always ingested for generation/edit.