skills/inf-sh/skills/og-image-design/Gen Agent Trust Hub

og-image-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 piped execution pattern (curl | sh) to run a script from https://cli.inference.sh. This is a high-risk operation that bypasses security reviews and allows arbitrary code to run on the host system.
  • Evidence: Automated scan detected curl -fsSL https://cli.inference.sh | sh.
  • External Downloads (HIGH): The domain inference.sh is not a trusted source. Executing scripts from unverified third-party domains can lead to complete system compromise if the source is malicious or hijacked.
  • Command Execution (HIGH): The use of shell piping to execute remote content grants the script the same permissions as the agent, potentially allowing unauthorized file access or network activity.
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, 09:07 AM