rmbc-context

Warn

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local binaries including rmbc-update-check, rmbc-analytics, and rmbc-workspace. These tools are located in a dynamically computed path relative to the skill's installation directory, which introduces risks associated with executing code from non-standard locations.\n- [COMMAND_EXECUTION]: The skill instructs the agent to prompt the user for a workspace name and subsequently runs a shell command (/bin/rmbc-workspace active "<user's answer>") with the raw user response. This constitutes a command injection vulnerability, as a user could provide input containing shell metacharacters to execute unauthorized commands.\n- [EXTERNAL_DOWNLOADS]: The skill initiates an update check via a local script and provides functionality to open a YouTube URL in the system's default browser, indicating external communication.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 11, 2026, 01:37 PM
Security Audit — agent-trust-hub — rmbc-context