dreamina-inspiration-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's example code and API calls require inserting a user's sessionid cookie value directly into request headers (Cookie: sessionid=...), which forces the agent to handle and emit a secret value verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The skill calls the public API endpoints (e.g., https://jimeng.jianying.com/mweb/v1/get_explore and /mweb/search/v1/guess) to retrieve item_list entries (authors, cover URLs and user-generated prompts/images) and the agent is expected to read and use those third-party, user-provided prompts/images as part of its workflow, which could enable indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill makes runtime POST requests to https://jimeng.jianying.com/mweb/v1/get_explore (and related jimeng.jianying.com endpoints) which return "aigc_image_params.text2image_params.prompt" values that are used as generation prompts, so the external content directly controls prompts and is required for the skill.