data-visualization

Fail

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • Remote Code Execution (CRITICAL): The skill employs the highly dangerous curl | sh pattern using the URL https://cli.inference.sh. This method executes remote code immediately upon download without any local validation or integrity checks.
  • External Downloads (HIGH): The script is fetched from an untrusted external domain (inference.sh) which is not included in the list of trusted providers. This poses a significant supply chain risk where the remote content could be replaced with malware at any time.
  • Command Execution (HIGH): By piping remote content directly into a shell interpreter, the skill bypasses typical security controls and grants the remote script the same privileges as the user running the agent.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 18, 2026, 02:00 AM
Security Audit — agent-trust-hub — data-visualization