verify-refs

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local Python script, scripts/verify-refs.py, which is the intended mechanism for processing reference data.
  • [EXTERNAL_DOWNLOADS]: The skill connects to well-known academic metadata services, including CrossRef, Semantic Scholar, and arXiv, to verify citation details. These are trusted services for research metadata.
  • [SAFE]: The skill processes user-provided file content, representing a surface for indirect prompt injection. 1. Ingestion points: Untrusted content enters the agent context from user-specified .bib or Markdown files. 2. Boundary markers: No delimiters or instructions are specified to isolate processed data from agent instructions. 3. Capability inventory: The skill has access to the Bash tool for script execution and WebFetch for online verification. 4. Sanitization: No sanitization or validation of the input file content is defined in the skill workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 03:19 AM
Security Audit — agent-trust-hub — verify-refs