md-to-pdf

Warn

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the pandoc command to convert markdown files into styled HTML.
  • [COMMAND_EXECUTION]: The skill invokes the Google Chrome application from a specific macOS path in headless mode to generate the PDF output.
  • [COMMAND_EXECUTION]: The command used to run Chrome includes the --no-sandbox flag. This flag disables the browser's security sandbox, which is intended to isolate the rendering process from the rest of the system, increasing the risk if the input HTML is malicious.
  • [COMMAND_EXECUTION]: The skill uses the rm command to delete the intermediate HTML file created during the process.
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection by processing untrusted markdown data.
  • Ingestion points: The skill reads input from user-provided .md files.
  • Boundary markers: None. There are no instructions or delimiters used to ensure the agent ignores any instructions potentially embedded within the markdown content.
  • Capability inventory: The skill has access to shell command execution (pandoc, Google Chrome, rm) and file system access.
  • Sanitization: No sanitization, escaping, or validation is performed on the markdown content before it is processed by the external tools.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 11, 2026, 10:31 AM
Security Audit — agent-trust-hub — md-to-pdf