ai-avatar-video

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an installation script for the infsh CLI tool hosted on the vendor's repository (github.com/inference-sh).
  • [COMMAND_EXECUTION]: Shell commands are used to interact with the inference.sh CLI to run AI models and manage apps, correctly restricted by the allowed-tools configuration.
  • [PROMPT_INJECTION]: The skill processes user-supplied media URLs and text prompts, which represents a surface for indirect prompt injection.
  • Ingestion points: Processes image_url, audio_url, prompt, and text fields in the SKILL.md workflows.
  • Boundary markers: No specific delimiters or warnings are used to separate user-provided data from command parameters.
  • Capability inventory: Utilizes the infsh command to run various AI applications.
  • Sanitization: No visible sanitization or validation of input content is performed before interpolation into commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 04:25 PM
Security Audit — agent-trust-hub — ai-avatar-video