technical-blog-writing
Fail
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- Remote Code Execution (CRITICAL): The skill uses a highly dangerous pattern where a remote script is piped directly into a shell interpreter.
- Evidence: Found command
curl -fsSL https://cli.inference.sh | shreported in automated scan. - Risk: This method bypasses all security checks and allows the remote server at
cli.inference.shto execute arbitrary code on the host machine. - External Downloads (HIGH): The skill attempts to download and execute content from
https://cli.inference.sh, which is not a recognized trusted source. - Evidence: Target URL
https://cli.inference.shis not among the whitelisted or trusted domains provided in the security skill configuration.
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