skills/ycmjason/tixmd/tixmd-init/Gen Agent Trust Hub

tixmd-init

Warn

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses pnpx to download and execute the @tixmd/cli package from the public NPM registry at runtime.
  • [COMMAND_EXECUTION]: The skill constructs a shell command (pnpx @tixmd/cli init --title "<project name>" --body "<body>") by interpolating strings gathered directly from user conversation. This pattern is susceptible to shell injection if the project name or body contains malicious shell metacharacters.
  • [COMMAND_EXECUTION]: Indirect Prompt Injection Surface Analysis:
  • Ingestion points: User-provided project name, description, tech stack, and conventions gathered during the interactive session (SKILL.md).
  • Boundary markers: None; the input is directly placed into command arguments.
  • Capability inventory: Execution of arbitrary shell commands through the pnpx call (SKILL.md).
  • Sanitization: The instructions do not define any sanitization, escaping, or validation logic for the user-supplied strings before they are passed to the CLI.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 22, 2026, 05:33 PM
Security Audit — agent-trust-hub — tixmd-init