aminer-free-academic

Pass

Audited by Gen Agent Trust Hub on Nov 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes and displays data from the AMiner API, which contains content provided by third parties.\n
  • Ingestion points: Data such as paper abstracts, scholar interests, and institution names are fetched from datacenter.aminer.cn and included in the agent's context.\n
  • Boundary markers: The instructions do not define delimiters or warnings to treat API-returned content as untrusted.\n
  • Capability inventory: The skill uses curl to perform network operations and reads environment variables (AMINER_API_KEY).\n
  • Sanitization: There are no requirements to sanitize or escape the external content before it is processed by the agent.\n- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, specifically curl for API calls and a bash script to check for the presence of the AMINER_API_KEY environment variable. While these target official vendor resources, the use of a shell environment for these tasks is a potential security surface if user-supplied parameters are not properly escaped.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 15, 2026, 08:47 AM