gpt2api-image-generator

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

• Third-party content exposure detected (high risk: 0.90). The skill sends prompts to a configured external GPT2API public endpoint (base_url in .bridge-private/gpt2api-image.json) and the script generate_gpt2api_image.py parses the API's JSON "data" (including optional "revised_prompt") and may download image URLs from that response, so untrusted third‑party content is ingested and can materially influence subsequent outputs or actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill sends user prompts at runtime to the configured GPT2API base URL (e.g., https://ackingliu.top/api/gpt2api) and explicitly ingests any returned "revised_prompt" values into its results, so remote content from that endpoint can directly modify agent prompts and is a required runtime dependency.