skills/uxfion/skills/paper-read/Gen Agent Trust Hub

paper-read

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of local shell commands via subprocess.run and os.execvp to coordinate between sibling tools (p2z.py, ocr.py) and standard utilities like pdftotext. These operations are fundamental to the skill's purpose of local file management and Zotero integration and do not involve unsanitized external input.
  • [EXTERNAL_DOWNLOADS]: The skill references sibling dependencies paper-to-zotero and paddleocr. While these are external extensions, they are treated as trusted components of the user's research environment. Standard tools like poppler (for pdftotext) and uv (for Python script execution) are also expected requirements for this type of technical agent skill.
  • [SAFE]: No evidence of prompt injection, data exfiltration to unauthorized domains, or malicious persistence mechanisms was found. The logic focuses on bibliographic data management and local document analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 08:23 AM