muapi-rednote-cover
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: No malicious behavior or critical security vulnerabilities were detected in the skill's implementation.\n- [PROMPT_INJECTION]: The skill uses user-supplied text to construct prompts for an image generation model, which is a potential surface for indirect prompt injection.\n
- Ingestion points: The
topic,style, andtext_overlayinputs inSKILL.mdare passed directly into the generation prompt.\n - Boundary markers: The prompt templates do not include specific delimiters or instructions to ignore potential injection content within the user inputs.\n
- Capability inventory: The agent uses the
muapiCLI orcurlto interact with image generation and editing models.\n - Sanitization: There is no evidence of input validation or sanitization before the user data is used in prompts.\n- [COMMAND_EXECUTION]: The skill relies on shell commands (
muapiandcurl) to perform its core functions. These commands are used as intended for communication with the developer's API and use standard authentication via environment variables.
Audit Metadata