image-to-video
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 provides instructions to execute 'curl -fsSL https://cli.inference.sh | sh'. This is a highly dangerous pattern that downloads a script from a non-whitelisted domain and pipes it directly into the shell for execution, bypassing any manual or automated verification of the script content.
- [EXTERNAL_DOWNLOADS] (MEDIUM): The skill references multiple external modules using 'npx skills add inference-sh/skills@...'. These modules are hosted on an external registry and are not from trusted organizations (e.g., Anthropic, OpenAI, Microsoft), introducing a significant supply chain risk where the remote code could be modified by the provider at any time.
- [COMMAND_EXECUTION] (LOW): The skill defines 'allowed-tools: Bash(infsh *)', granting the agent the ability to execute shell commands. While necessary for the intended functionality, this capability directly facilitates the execution of the critical remote code execution findings mentioned above.
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