paper2reel

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill utilizes the subprocess module to run external utilities such as ffmpeg and pdftoppm. These tools are essential for video clip generation and PDF-to-image conversion. The skill handles command arguments as lists, which is a recommended practice to avoid shell injection vulnerabilities.
  • External Downloads: During the build process, the skill may download the MathJax library from the official NPM registry to ensure that mathematical notations can be rendered offline in the final viewer. This involves fetching a tarball from a well-known service and extracting it locally.
  • Indirect Prompt Injection: The skill processes various artifacts from research papers, including text and metadata. While these are used to populate the viewer's alignment map, the ingestion of external data constitutes a potential surface for indirect prompt injection that warrants standard safety considerations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 04:13 PM
Security Audit — agent-trust-hub — paper2reel