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

tixmd-new

Warn

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses pnpx to fetch and execute the @tixmd/cli package from the npm registry.
  • [REMOTE_CODE_EXECUTION]: By using pnpx, the skill performs remote code execution of an external package during runtime.
  • [COMMAND_EXECUTION]: The skill dynamically assembles and executes shell commands using data gathered from user input and file content. This presents a risk of command injection if the input strings are not properly handled by the platform.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection.
  • Ingestion points: Context is read from .tixmd/project.md and output is captured from the board listing command.
  • Boundary markers: No specific delimiters or safety instructions are used to separate untrusted data from core instructions.
  • Capability inventory: The skill is capable of executing shell commands and creating filesystem-backed ticket entries via the CLI tool.
  • Sanitization: There is no evidence of sanitization or validation of the content read from external files or command outputs before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 22, 2026, 05:34 PM
Security Audit — agent-trust-hub — tixmd-new