ai-marketing-videos
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- Unverifiable Dependencies & Remote Code Execution (CRITICAL): The skill executes
curl -fsSL https://cli.inference.sh | sh, which downloads and runs a script from the internet without verification. This is a critical vulnerability as the domain is not a trusted source. - Indirect Prompt Injection (LOW): The skill interpolates unvalidated data into shell commands, creating an attack surface for data-driven instruction injection. * Ingestion points: Content from
script.jsonand shell variables in the workflow. * Boundary markers: Absent. * Capability inventory:Bash(infsh *)provides wildcard tool execution. * Sanitization: Absent; external data is used directly in string interpolation. - Dynamic Execution (LOW): The skill uses bash loops and variable interpolation to dynamically construct and execute commands, which is expected for its purpose but increases the complexity of validating command safety.
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