ai-automation-workflows
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION] (CRITICAL): The skill utilizes a piped remote execution pattern:
curl -fsSL https://cli.inference.sh | sh. This is a confirmed critical vulnerability as it allows unverified, arbitrary code from a non-trusted external source to be executed with the privileges of the user. - [EXTERNAL_DOWNLOADS] (HIGH): The skill downloads and executes scripts from
https://cli.inference.sh. This domain is not part of the established Trusted External Sources list (e.g., GitHub official orgs, verified package registries), making the source unverifiable. - [COMMAND_EXECUTION] (MEDIUM): The skill's primary purpose is to orchestrate workflows using bash scripts and a Python SDK. While this is the intended functionality, combined with the insecure installation method, it provides a powerful post-exploitation surface for an attacker.
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