muapi-interior-design
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: Vulnerability to indirect prompt injection due to the handling of external data.
- Ingestion points: User-provided inputs such as
room_type,design_style, andcolor_paletteare ingested inSKILL.md. - Boundary markers: The skill lacks delimiters or explicit instructions for the agent to treat user input as untrusted data or to ignore embedded instructions.
- Capability inventory: The agent is authorized to execute
muapiCLI tools andcurlcommands to interact with remote endpoints (SKILL.md). - Sanitization: There are no instructions for sanitizing or escaping the user inputs before they are interpolated into the final prompt or command strings.
- [COMMAND_EXECUTION]: The skill instructs the agent to construct and execute shell commands using
muapiandcurlfor API interaction. This pattern relies on the agent's ability to safely handle shell metacharacters in user-supplied variables, which is a potential risk factor in the absence of explicit sanitization logic.
Audit Metadata