Skills
skills/firecrawl/skills/doc/Gen Agent Trust Hub

doc

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Recommends standard, reputable packages (libreoffice, poppler, python-docx) from official system and language repositories.
  • [COMMAND_EXECUTION]: Uses subprocess.run with list-based arguments to execute soffice and pdftoppm in scripts/render_docx.py, which prevents shell injection.
  • [PROMPT_INJECTION]: Processing external documents creates an indirect prompt injection surface.
  • Ingestion points: Document reading workflow in SKILL.md and file input in scripts/render_docx.py.
  • Boundary markers: None.
  • Capability inventory: System binary execution and local file writing.
  • Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 08:24 PM