seo-content-brief
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [Remote Code Execution] (CRITICAL): The skill performs remote code execution by downloading a script and piping it directly into the shell (
curl | sh). This is a high-risk pattern that allows an untrusted third party (inference.sh) to execute arbitrary commands on the system. - Evidence:
curl -fsSL https://cli.inference.sh | shdetected in automated scan report. - [External Downloads] (MEDIUM): The skill references an external domain (
cli.inference.sh) that is not part of the established trusted source list. Any changes to the content at this URL could compromise the security of the agent environment.
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