muapi-brand-kit
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates external user inputs (brand_name, industry, personality, color_preference) directly into prompts for image generation tools, creating an attack surface for indirect prompt injection.
- Ingestion points: User inputs defined in the SKILL.md frontmatter are interpolated into Phase A generation steps.
- Boundary markers: No delimiters or specific instructions are used to separate user-provided data from system instructions.
- Capability inventory: The skill utilizes the muapi CLI and curl network commands to generate content.
- Sanitization: No logic for validating, escaping, or filtering user-provided inputs is defined.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands and perform network operations to interact with the MuAPI service via the muapi CLI and curl fallback commands to api.muapi.ai.
Audit Metadata