llm-models
Fail
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION] (CRITICAL): The installation instructions include
curl -fsSL https://cli.inference.sh | sh. This pattern is highly dangerous as it executes unverified code from the internet directly on the user's system without prior inspection.- [EXTERNAL_DOWNLOADS] (HIGH): The skill relies on an external binary and installation script frominference.sh, which is not a verified or trusted source organization. There is no cryptographic verification of the script content before execution.- [COMMAND_EXECUTION] (MEDIUM): The skill requests broad permissions forBash(infsh *)to execute tools that are installed via the aforementioned insecure remote execution method.
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