skills/horuz-ai/claude-plugins/docx/Gen Agent Trust Hub

docx

Fail

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The SKILL.md file contains mandatory instructions for the agent to "NEVER set any range limits" when reading documentation files, a technique that can be used to bypass safety filters or force the agent to consume large instruction sets containing malicious payloads.\n- [COMMAND_EXECUTION]: The scripts ooxml/scripts/unpack.py and ooxml/scripts/validation/docx.py use zipfile.ZipFile.extractall() without validating archive member paths. This creates a Zip Slip vulnerability, allowing a malicious document to overwrite arbitrary files on the system.\n- [COMMAND_EXECUTION]: The skill's setup documentation instructs the agent to use sudo apt-get install to install system dependencies like pandoc, libreoffice, and poppler-utils, which presents a significant privilege escalation risk.\n- [COMMAND_EXECUTION]: Validation modules in the ooxml/scripts/validation/ directory use the lxml library for parsing XML files without explicitly disabling entity resolution, potentially exposing the system to XML External Entity (XXE) attacks.\n- [EXTERNAL_DOWNLOADS]: The skill documentation requires the global installation of the docx library via NPM and several system packages.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 27, 2026, 05:32 PM