muapi-product-showcase-video
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill takes user input and uses it to build prompts for AI generation tools, creating a surface for potential indirect prompt injection.
- Ingestion points: 'ingredients_description' and 'brand_colors' in SKILL.md.
- Boundary markers: No delimiters or warnings are used for interpolated user data.
- Capability inventory: The skill uses 'muapi' CLI and 'curl' commands to interact with external services.
- Sanitization: No data sanitization is performed on user inputs.
- [COMMAND_EXECUTION]: The skill instructions involve executing shell commands such as 'muapi' and 'curl' to perform API interactions and authentication.
Audit Metadata