citation-verification

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill communicates with well-known academic metadata providers to validate reference information.\n
  • Interfaces with api.crossref.org, doi.org, export.arxiv.org, and api.semanticscholar.org to fetch publication data.\n- [COMMAND_EXECUTION]: Includes local Python scripts intended for citation analysis and formatting validation.\n
  • Provides scripts/verify-citations.py, scripts/api-clients.py, and scripts/format-checker.py to be executed by the agent.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external citation files (BibTeX and LaTeX), representing an ingestion surface for potentially untrusted data.\n
  • Ingestion points: scripts/verify-citations.py and scripts/format-checker.py read bibliographic content from local .bib and .tex files.\n
  • Capability inventory: The skill has the capability to perform network requests to academic APIs and write report files based on processed input.\n
  • Sanitization: Employs the bibtexparser library for structured parsing of bibliographic entries.\n
  • Boundary markers: The skill does not implement specific safety delimiters or ignore-instructions warnings for the processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 03:43 PM