AGENT LAB: SKILLS

competitor-teardown

Fail

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [Remote Code Execution] (CRITICAL): The skill uses a 'curl | sh' pattern to download and execute code from 'https://cli.inference.sh'. This pattern is highly dangerous as it grants a remote server full control over the execution environment.
  • [External Downloads] (HIGH): The skill attempts to download resources from a domain that is not part of the Trusted External Sources list. Under the assume-malicious posture, this is treated as a high-risk external dependency.
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