skills/ainergiz/mac-setup-guide/docx/Gen Agent Trust Hub

docx

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes external CLI tools including soffice, git, and pandoc for document validation, comparison, and structured text extraction. These operations use argument-list invocation via the subprocess module, which prevents shell injection vulnerabilities.\n- [PROMPT_INJECTION]: The skill processes untrusted document data, creating a surface for indirect prompt injection.\n
  • Ingestion points: Processes raw XML from .docx archives and converts document content to markdown via pandoc.\n
  • Boundary markers: Lacks explicit delimiters or markers to isolate untrusted text from extracted documents before it is returned to the agent context.\n
  • Capability inventory: Includes file system writing via the custom Document class and execution of system binaries.\n
  • Sanitization: Robustly utilizes the defusedxml library for XML parsing across all core scripts to prevent XML External Entity (XXE) and quadratic expansion attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 08:02 AM