AGENT LAB: SKILLS

character-design-sheet

Fail

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • Unverifiable Dependencies & Remote Code Execution (CRITICAL): The skill utilizes a highly dangerous pattern curl -fsSL https://cli.inference.sh | sh to download and execute code from an untrusted source.
  • External Downloads (MEDIUM): Execution of content from https://cli.inference.sh is unverifiable as the source is not listed in the trusted repositories or organizations.
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, 11:29 PM