grok-build
Fail
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides installation instructions that involve downloading a setup script from x.ai's official domain and piping it directly to a shell for execution.
- [COMMAND_EXECUTION]: The skill relies on the
run_terminal_commandtool to execute thegrokCLI binary and manage local system operations as part of its core functionality. - [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by facilitating the autonomous processing of local repository files and user-provided prompts by a sub-agent.
- Ingestion points: Local codebase files and user-provided tasks processed by the
grokCLI (SKILL.md). - Boundary markers: None specified in the instructions to separate untrusted data from the agent's control logic.
- Capability inventory: The
grokCLI (invoked viarun_terminal_command) has broad capabilities including file modification, terminal command execution, and sub-agent spawning across all reference files. - Sanitization: No sanitization or verification steps are required before the agent processes untrusted repository content.
Recommendations
- HIGH: Downloads and executes remote code from: https://x.ai/cli/install.sh - DO NOT USE without thorough review
Audit Metadata