skills/haomingz/kimi-skills/pdf/Gen Agent Trust Hub

pdf

Fail

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill includes instructions to download and execute code from an unverified remote server without any integrity checks.
  • Evidence found in routes/latex.md: cd ~ && curl -fsSL https://drop-sh.fullyjustified.net | sh && ls -la tectonic. This command pipes a remote script directly into the shell, granting the external source full execution rights on the system.
  • Evidence found in scripts/setup.sh: curl -fsSL https://drop-sh.fullyjustified.net | sh.
  • [EXTERNAL_DOWNLOADS]: The skill is configured to automatically download and install software packages from various registries during operation.
  • The scripts/pdf.sh script executes npm install -g playwright and python3 -m pip install --user -U pikepdf pdfplumber to install dependencies at runtime.
  • The scripts/compile_latex.py script attempts to install the pypdf library via pip if it is not already available.
  • The scripts/browser_helper.js script may execute npx playwright install chromium to download and install a browser binary.
  • [COMMAND_EXECUTION]: The skill frequently executes system commands via subprocesses to manage files and perform document conversions.
  • scripts/cmd_convert.py calls LibreOffice (soffice) via subprocess.run to convert Office documents.
  • scripts/compile_latex.py calls the tectonic binary to compile LaTeX files.
  • scripts/browser_helper.js uses execSync and spawnSync to verify the environment and locate executables.
Recommendations
  • HIGH: Downloads and executes remote code from: https://drop-sh.fullyjustified.net - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Jun 19, 2026, 01:44 AM
Security Audit — agent-trust-hub — pdf