muapi-interior-design
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it interpolates untrusted user inputs directly into prompts and commands.
- Ingestion points: Text inputs for room_type, design_style, color_palette, and specific_elements are accepted from the user in SKILL.md.
- Boundary markers: No delimiters or protective instructions are provided to the agent to distinguish user data from the intended command structure.
- Capability inventory: The skill instructs the agent to use the muapi CLI and curl for API requests, which provides a functional surface for executing injected instructions.
- Sanitization: There is no requirement or logic provided for sanitizing or escaping the user-supplied text before it is used in shell commands or model prompts.
Audit Metadata