AGENT LAB: SKILLS

customer-persona

Fail

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • Remote Code Execution (CRITICAL): The skill uses a piped shell command to execute remote content directly from the internet.
  • Evidence: 'curl -fsSL https://cli.inference.sh | sh'.
  • Risk: This pattern allows an untrusted third party to execute any command on the host system without verification, version pinning, or security review.
  • External Downloads (HIGH): The skill references an external domain ('inference.sh') that is not included in the list of trusted GitHub organizations or repositories.
  • Command Execution (HIGH): The skill explicitly invokes the shell ('sh') to process unverified data retrieved from the network.
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 19, 2026, 03:41 AM