skills/modu-ai/moai-cowork/doc-pdf/Gen Agent Trust Hub

doc-pdf

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation in assets/fonts/README.md provides URLs to download font assets from the official Noto Fonts GitHub repository, which is a well-known and trusted source.- [COMMAND_EXECUTION]: The skill instructions include shell commands for downloading fonts and licenses using Python and curl.- [INDIRECT_PROMPT_INJECTION]: The skill accepts and processes untrusted data in Markdown, HTML, and JSON formats for PDF rendering, creating a potential vector for indirect instructions.
  • Ingestion points: User-supplied document content is processed via the styled_html and plain_html variables in SKILL.md.
  • Boundary markers: The skill does not implement explicit delimiters or 'ignore' instructions for the content being rendered.
  • Capability inventory: The rendering logic in SKILL.md includes file system write operations (write_pdf) and environment variable access.
  • Sanitization: There is no evidence of input sanitization or filtering before the content is passed to the rendering engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 10:14 AM