AGENT LAB: SKILLS

seo-content-brief

Fail

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • Remote Code Execution (CRITICAL): The automated scan detected a command (curl -fsSL https://cli.inference.sh | sh) that downloads a script from a remote server and executes it directly via the shell. This is a highly dangerous pattern that allows for arbitrary code execution without verification.
  • External Downloads (HIGH): The skill fetches executable content from an untrusted domain (cli.inference.sh). This domain is not included in the trusted external sources list, increasing the risk of supply chain attacks or malicious payload delivery.
  • Command Execution (HIGH): The use of piped shell commands (| sh) bypasses local security reviews and executes instructions with the privileges of the running agent.
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