citation-assistant-skill

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate functionality for academic citation management using transparent Python code.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves data from well-known academic services (api.openalex.org and api.crossref.org) using the standard requests library.
  • [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface because it processes untrusted paper metadata from external APIs. Ingestion points: search_papers and get_bibtex functions in SKILL.md. Boundary markers: Absent. Capability inventory: File system write access in build_bibliography (SKILL.md). Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 10:16 PM