technical-blog-writing

Fail

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • Remote Code Execution (CRITICAL): The skill executes a remote script using the 'curl | sh' pattern which is a high-risk operation. * Evidence: Automated detection of 'curl -fsSL https://cli.inference.sh | sh'. * Risk: This allows the host at cli.inference.sh to execute any command on the user's machine with the permissions of the agent.
  • External Downloads (HIGH): The skill downloads content from inference.sh, which is not on the list of trusted external sources. * Evidence: URL https://cli.inference.sh. * Risk: Untrusted sources can serve malicious payloads or be compromised via DNS hijacking or server-side attacks.
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, 01:54 AM