aminer-academic-search
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFE
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill requires an
AMINER_API_KEYto function. The provided instructions and code follow secure practices by retrieving this key from environment variables rather than hardcoding it. TheSKILL.mdexplicitly warns: 'Only check whether AMINER_API_KEY exists; never expose the token in plain text anywhere'. - [EXTERNAL_DOWNLOADS]: The skill connects to
https://datacenter.aminer.cnto perform academic searches. This is the legitimate endpoint for the vendor (AMiner). No unauthorized third-party downloads were detected. - [REMOTE_CODE_EXECUTION]: No remote code execution patterns were found. The provided Python client uses standard libraries to facilitate API requests.
- [DYNAMIC_EXECUTION]: The Python script contains standard request-handling logic and does not use
eval(),exec(), or other unsafe dynamic execution patterns. - [INDIRECT_PROMPT_INJECTION]: As a search-based skill, it processes externally sourced academic data (abstracts, titles). While theoretically a surface for injection, the skill is scoped to academic contexts and lacks high-privilege dangerous capabilities that would make such an injection critical. The risk is considered low and standard for this class of tool.
Audit Metadata