Skills
skills/anentrypoint/plugforge/create-lang-plugin/Gen Agent Trust Hub

create-lang-plugin

Fail

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: HIGHCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides detailed implementation patterns utilizing child_process.execFileSync and child_process.spawnSync to execute arbitrary CLI tools and shell commands directly on the host operating system.
  • [REMOTE_CODE_EXECUTION]: The exec.run function is designed to execute arbitrary code blocks provided by the AI agent, effectively creating a mechanism for unvalidated code execution through various language runtimes or CLI tools.
  • [PROMPT_INJECTION]: The context field allows plugins to inject arbitrary strings into the prompt context via the additionalContext parameter, which lacks boundary markers or sanitization, creating a surface for manipulating agent behavior through data injection.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 22, 2026, 12:42 AM