add-plugin
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The instructions guide the agent to generate entrypoint scripts and execute them using the nucleo CLI, performing dynamic code execution on the host system.
- [COMMAND_EXECUTION]: The agent is tasked with running commands provided by the user to test the plugins, which allows for the execution of arbitrary shell commands.
- [PROMPT_INJECTION]: The skill ingests untrusted user input for plugin names and commands and incorporates them into executable scripts and shell commands without sanitization or boundary markers, creating a surface for indirect prompt injection.
Audit Metadata