ned-ai-helper

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing 'markdown' and 'weasyprint' via the pip package manager to enable its PDF output capability. These are standard, widely-recognized libraries for document processing.
  • [COMMAND_EXECUTION]: The skill makes use of the 'pandoc' command-line utility for converting generated markdown documents into DOCX format.
  • [REMOTE_CODE_EXECUTION]: A Python script is provided for the agent to convert markdown content into a styled PDF file. The script performs standard file reading and writing operations within the local environment and does not attempt network communication or access to sensitive system directories.
  • [PROMPT_INJECTION]: The skill's primary function involves analyzing user-provided AI proposals, which creates a potential surface for indirect prompt injection (Ingestion: SKILL.md; Boundary markers: Absent; Capabilities: Python-based file operations and Pandoc execution; Sanitization: Absent). This surface is managed through the use of structured governance frameworks, and the risk level is considered low and consistent with the skill's intended use.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 09:25 AM
Security Audit — agent-trust-hub — ned-ai-helper