skills/4444j99/a-i--skills/docx/Gen Agent Trust Hub

docx

Warn

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The script scripts/office/soffice.py contains an embedded C source string which is written to the system's temporary directory and compiled at runtime using gcc. The resulting shared library is then injected into the execution environment of LibreOffice using LD_PRELOAD to intercept and redirect system-level socket calls (socket, listen, accept). This is used to enable inter-process communication in restricted environments where standard Unix domain sockets are blocked.\n- [PRIVILEGE_ESCALATION]: The SKILL.md file provides instructions that include using sudo apt-get install for managing system-level dependencies such as pandoc, libreoffice, and poppler-utils. This encourages the agent to request or use administrative privileges, which is a high-risk pattern.\n- [COMMAND_EXECUTION]: The skill makes extensive use of system command execution via subprocess.run() across several scripts. This includes compiling C code with gcc, running LibreOffice (soffice), converting PDF files with pdftoppm, and performing structural extraction with pandoc and git.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Word documents as its primary function. Because the skill possesses high-level system capabilities (including command execution and macro usage), it has a vulnerability surface for indirect prompt injection. A maliciously crafted document could potentially influence the agent's behavior during content extraction or analysis.\n
  • Ingestion points: Document text extracted via pandoc in SKILL.md and raw XML content from word/document.xml read by the Document class in scripts/document.py.\n
  • Boundary markers: The instructions do not specify strict boundary delimiters or 'ignore instruction' directives when processing external document content.\n
  • Capability inventory: Powerful capabilities including file system access, subprocess execution of multiple system tools (soffice, gcc, pandoc), and execution of LibreOffice macros.\n
  • Sanitization: While the skill uses defusedxml to mitigate XML-specific attacks, there is no evidence of natural language instruction sanitization for processed document content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 6, 2026, 04:23 PM