bib-verify

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the py-openjudge and litellm Python packages from the standard PyPI registry.
  • [COMMAND_EXECUTION]: The skill uses python -m cookbooks.paper_review to execute its verification logic. This involves running a local Python module that performs network lookups and file I/O operations to generate reports.
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8).
  • Ingestion points: The tool parses and processes external .bib files provided by the user.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are mentioned for the content within the BibTeX entries.
  • Capability inventory: The skill performs network requests to academic databases (CrossRef, arXiv, DBLP) and writes output reports to the filesystem.
  • Sanitization: The skill lacks explicit sanitization for the fields extracted from the .bib file before they are included in the generated markdown report, which could be used to influence the agent's interpretation of the verification results.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 03:41 AM