youtube-thumbnail-design

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool for executing AI models. The execution environment is restricted to this specific toolset via the allowed-tools frontmatter configuration.
  • [EXTERNAL_DOWNLOADS]: The skill references and installs external components from the inference-sh and belt-sh GitHub repositories to facilitate AI image generation.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes an attack surface for indirect prompt injection as it interpolates user-provided prompts into the input for the belt tool. Evidence Chain: 1. Ingestion points: --input JSON payload in belt app run (SKILL.md); 2. Boundary markers: Absent; 3. Capability inventory: belt app run (SKILL.md); 4. Sanitization: Absent. This is a standard feature of AI generation tools used in accordance with the skill's primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:23 PM
Security Audit — agent-trust-hub — youtube-thumbnail-design