last30days

Fail

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill facilitates the installation of the Grok CLI using an insecure method (curl -fsSL https://x.ai/cli/install.sh | bash) that executes a remote script directly on the host machine without verification, posing a risk of arbitrary code execution.
  • [COMMAND_EXECUTION]:
  • Automated scanners identified scripts/lib/digg.py as a malicious malware file. This script is a core component for processing Digg research data.
  • The skill uses subprocess.run and subprocess.Popen in numerous files, including scripts/box_chrome_login.py and scripts/verify_v3.py, to execute system binaries and external CLI tools, increasing the potential attack surface for command injection.
  • [EXTERNAL_DOWNLOADS]:
  • Multiple research-related URLs under the https://di.gg/ai domain were flagged as phishing threats by automated scanners.
  • The skill dynamically downloads and executes various 'Printing Press' CLI utilities from external sources during its setup and execution phases.
  • [DATA_EXFILTRATION]:
  • The skill contains specialized components in scripts/lib/agentcookie.py and scripts/lib/chrome_cdp.py designed to extract sensitive session cookies (auth_token and ct0) from the user's browser databases to access X/Twitter accounts.
  • It is configured to transmit research findings and rendered reports to an external publishing service at api.ht-ml.app.
  • Search queries and metadata are distributed to multiple third-party API endpoints, including api.scrapecreators.com and xquik.com.
  • [PRIVILEGE_ESCALATION]: The diagnostic module in scripts/lib/health.py instructs the agent to suggest using sudo for system-level package management operations.
Recommendations
  • HIGH: Downloads and executes remote code from: https://x.ai/cli/install.sh - DO NOT USE without thorough review
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
  • AI detected serious security threats
  • Contains 3 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 16, 2026, 10:41 PM