prompt-engineering
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 contains the command
curl -fsSL https://cli.inference.sh | sh. This is a high-risk pattern that pipes an external, unverified script directly into the shell for execution. The domaincli.inference.shis not a trusted source, making this a classic vector for arbitrary code execution and system compromise. - [EXTERNAL_DOWNLOADS] (HIGH): The skill references multiple external dependencies and related skills from the
inference-shorganization usingnpx skills add. Since this organization is not in the predefined list of trusted providers, these downloads represent an unverified supply chain risk. - [COMMAND_EXECUTION] (MEDIUM): The skill is configured with
allowed-tools: Bash(infsh *), granting it the ability to execute theinfshcommand-line tool. This tool is installed via the dangerous RCE method mentioned above, meaning the agent would be operating a tool of unknown integrity.
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