paper-2-web
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for cloning its official source code from a public GitHub repository (https://github.com/YuhangChen1/Paper2All.git) and installing standard document processing utilities like LibreOffice and Poppler. These are typical setup procedures for the stated functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process academic papers, which are external data sources, creating a potential surface for indirect prompt injection. This is a core part of its intended functionality and no evidence of exploitation was found.
- Ingestion points: LaTeX source files and PDF documents provided in the user's input directory (documented in SKILL.md).
- Boundary markers: No specific delimiters or boundary warnings are mentioned in the provided documentation.
- Capability inventory: The skill executes Python scripts for content extraction, slide generation, and video rendering using external API models.
- Sanitization: The instructions do not detail specific sanitization or filtering steps applied to the ingested paper content.
Audit Metadata