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
beltCLI tool for executing AI models. The execution environment is restricted to this specific toolset via theallowed-toolsfrontmatter configuration. - [EXTERNAL_DOWNLOADS]: The skill references and installs external components from the
inference-shandbelt-shGitHub 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
belttool. Evidence Chain: 1. Ingestion points:--inputJSON payload inbelt 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