AGENT LAB: SKILLS

email-design

Fail

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • Remote Code Execution (HIGH): The skill uses a highly dangerous pattern (curl | sh) to execute a script from an unverified URL (https://cli.inference.sh). This allows the remote server to execute arbitrary commands on the host machine.
  • External Downloads (MEDIUM): The skill attempts to download and execute content from inference.sh, which is not included in the list of trusted repositories or organizations, presenting a significant supply chain risk.
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
HIGH
Analyzed
Feb 18, 2026, 11:50 PM