ai-video-generation
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 documentation recommends installing the
infshCLI usingcurl -fsSL https://cli.inference.sh | sh. This is a confirmed remote code execution pattern that executes unverified code from an external, untrusted source directly on the host system. - External Downloads (HIGH): The skill relies on fetching scripts and binaries from
inference.sh, which is not among the predefined trusted organizations or repositories. - Indirect Prompt Injection (LOW): The skill provides a surface for injection by interpolating untrusted user data into shell commands. 1. Ingestion points: User-provided prompts and URLs are used as inputs for
infshcommands inSKILL.md. 2. Boundary markers: No delimiters or warnings are present in the command templates. 3. Capability inventory: The skill utilizesBash(infsh *)to execute generative commands. 4. Sanitization: There is no evidence of sanitization or validation of external content before interpolation.
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