aminer-data-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs embedding the API token into requests and command-line arguments (Authorization: <your_token>, --token ), which requires the LLM to place secret values verbatim into generated commands/requests.

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

• Third-party content exposure detected (high risk: 0.90). This skill (see scripts/aminer_client.py and SKILL.md) directly queries AMiner's public API endpoints at https://datacenter.aminer.cn/gateway/open_platform (e.g., /api/paper/detail, /api/person/detail, /api/paper/qa/search), ingests abstracts, bios and other public records, and uses those results to select IDs and drive follow-up API calls, so untrusted third‑party content can materially influence the agent's next actions.