grok-deep-research

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the grok CLI binary via the subprocess.run function in scripts/grok_deep_research.py. The implementation uses a list-based argument structure and avoids the use of shell=True, effectively preventing shell injection vulnerabilities at the host level.
  • [PROMPT_INJECTION]: Research prompts are constructed by interpolating user-provided queries. The skill implements a robust security layer by passing --deny flags (denying Bash(*), write_file, edit_file, and apply_patch) to the grok CLI. This ensures the Grok agent remains in a restricted, read-only research mode even if the processed content contains adversarial instructions.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from the web. However, the potential impact is mitigated by the mandatory exclusion of high-privilege tools (shell, file writing) in the grok CLI invocation, reducing the agent's capability to perform harmful actions based on external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 09:56 AM
Security Audit — agent-trust-hub — grok-deep-research