crossref-database

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill interacts with the CrossRef REST API via the habanero library. CrossRef is a well-known and trusted metadata provider for scholarly publications and no suspicious network behavior or data exfiltration attempts were detected.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface common to tools processing external data.
  • Ingestion points: Bibligraphic metadata (titles, author names, abstracts) retrieved from the CrossRef API in scripts/query_crossref.py.
  • Boundary markers: Absent. The script provides raw JSON output without delimiters or ignore-instructions for the agent.
  • Capability inventory: The skill is designed to execute local Python scripts via the shell and produce markdown files.
  • Sanitization: Absent. The retrieved data is not filtered or escaped before being presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 02:34 AM
Security Audit — agent-trust-hub — crossref-database