AGENT LAB: SKILLS

ai-automation-workflows

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 automated scan detected the pattern curl -fsSL https://cli.inference.sh | sh. This is a critical security vulnerability where a remote script is executed with shell privileges without any integrity verification or user intervention.
  • External Downloads (HIGH): The domain inference.sh is not on the list of trusted external sources. Downloading and executing content from unverified sources is a high-risk activity.
  • Command Execution (HIGH): The use of piped shell execution (| sh) bypasses local security auditing and allows the remote server to determine exactly what commands are run on the user's machine.
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, 11:35 PM