skills/1nfsh/skills/customer-persona/Gen Agent Trust Hub

customer-persona

Fail

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • Unverifiable Dependencies & Remote Code Execution (CRITICAL): The automated scan detected a piped shell command 'curl -fsSL https://cli.inference.sh | sh'. This pattern is a high-risk execution vector that downloads and immediately runs a script from the internet without user inspection or verification.
  • External Downloads (CRITICAL): The skill attempts to download executable content from 'https://cli.inference.sh', which is not a trusted domain according to the security policy. This bypasses typical software supply chain security controls.
  • Command Execution (CRITICAL): The use of shell piping ('| sh') to execute remote content grants the remote script full command execution privileges under the current user context, potentially leading to complete system compromise.
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, 01:42 AM
Security Audit — agent-trust-hub — customer-persona