explainer-video-guide

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references external installation instructions and scripts (e.g., https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md) and suggests installing CLI tools via package managers. These references are essential for the skill's stated purpose of utilizing the inference.sh platform.
  • [INDIRECT_PROMPT_INJECTION]: The skill documents how to pass user-defined prompts into CLI commands for video and audio generation, creating a potential surface for indirect prompt injection if the inputs are not sanitized.
  • Ingestion points: User-supplied strings in the prompt field of JSON inputs within the SKILL.md file.
  • Boundary markers: Data is passed as structured JSON objects within shell command arguments.
  • Capability inventory: The skill utilizes the Bash(belt *) tool to execute remote AI models for video, audio, and image generation.
  • Sanitization: No explicit sanitization or filtering of user input is described; the skill relies on the underlying platform's safety guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:13 PM
Security Audit — agent-trust-hub — explainer-video-guide