Skills
Navigate
skills/fengjiehzi/skills/aminer-data-search/Gen Agent Trust Hub

aminer-data-search

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/aminer_client.py uses globals().get() in its raw action to dynamically invoke functions based on command-line arguments. This allows the execution of functions defined within the script's namespace based on external input.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from the AMiner API (such as abstracts and biographies), creating an indirect prompt injection surface where malicious instructions in academic text could influence agent behavior. \n
  • Ingestion points: scripts/aminer_client.py (fetches data from datacenter.aminer.cn) \n
  • Boundary markers: Absent \n
  • Capability inventory: Network requests via urllib in scripts/aminer_client.py \n
  • Sanitization: Absent.
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to the AMiner Open Platform API at https://datacenter.aminer.cn to retrieve academic data, which is its core intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 06:45 AM