NYC

openalex-database

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill is vulnerable to indirect prompt injection (Category 8) due to the ingestion of untrusted data from the OpenAlex API which is then presented to the agent. \n
  • Ingestion points: scripts/query_helpers.py (via API requests) and references/common_queries.md (via requests.get). \n
  • Boundary markers: Absent in the provided code and documentation examples. \n
  • Capability inventory: The skill performs network requests and file-write operations (quantum_papers.csv). \n
  • Sanitization: No validation or escaping of API-returned strings is implemented before the data is processed or printed.\n- [EXTERNAL_DOWNLOADS] (LOW): The skill performs network operations to external domains (OpenAlex API) that are not on the trusted sources list. \n
  • Evidence: Use of requests.get in references/common_queries.md and internal request helpers in scripts/query_helpers.py.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:55 PM