document-skills

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill consists of documentation and legitimate code examples for academic research workflows. No obfuscation, persistence mechanisms, or unauthorized privilege escalations were found.
  • [EXTERNAL_DOWNLOADS]: The skill references several external services and repositories for document parsing and research assistance, including anystyle.io for citation parsing and various GitHub-hosted Zotero plugins. These references are central to the skill's stated purpose.
  • [COMMAND_EXECUTION]: The guides provide standard command-line instructions for tools such as Pandoc, Docker, and package managers (pip, gem). These are used for converting documents between formats and deploying local document processing servers.
  • [PROMPT_INJECTION]: As a document processing suite, the skill inherently possesses a surface for indirect prompt injection from untrusted academic files.
  • Ingestion points: Untrusted data is ingested via PDF file parsing and external citation string inputs across multiple modules.
  • Boundary markers: Not explicitly implemented in the provided code snippets.
  • Capability inventory: Includes network requests (AnyStyle API), local server communication (GROBID), and file system writes for extracted assets.
  • Sanitization: Content is extracted as raw text without specific filtering of embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 01:52 AM
Security Audit — agent-trust-hub — document-skills