google-translate

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input which is then interpolated into shell commands. There is a risk that malicious input containing shell metacharacters could lead to command injection if not handled by the underlying execution layer.
  • Ingestion points: User-supplied content passed to the <text> parameter in the robomotion googletranslate translate command (defined in SKILL.md).
  • Boundary markers: None provided. There are no instructions for the agent to use delimiters or to treat the input as literal text.
  • Capability inventory: The skill utilizes command-line execution via the robomotion CLI.
  • Sanitization: No explicit sanitization or escaping instructions are included in the skill definition to protect against shell injection.- [COMMAND_EXECUTION]: The skill is entirely built around the execution of the robomotion CLI tool. It requires the installation of a specific package (robomotion install googletranslate) and executes multiple subcommands (connect, translate, disconnect) to perform its primary function.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 02:48 AM
Security Audit — agent-trust-hub — google-translate