amicro-design-system
Warn
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill specifies the use of 'npx @subhanhq/amicro@latest' to add components. This command downloads package data from the NPM registry. The package '@subhanhq/amicro' is not associated with the skill author 'gsfsss', representing an unverified external dependency.
- [REMOTE_CODE_EXECUTION]: The instruction to use 'npx' results in the execution of remote code fetched from the NPM registry at runtime. As the package source is not verified as belonging to the skill author, this represents a potential remote execution vector.
- [COMMAND_EXECUTION]: The CLI integration rules involve providing and potentially executing shell commands using 'npx' to manage the component registry and add UI components.
- [PROMPT_INJECTION]: The skill defines a process for ingesting external component data, creating an indirect prompt injection surface.
- Ingestion points: The agent is directed to read component source files in 'registry/ui/' and configuration metadata in 'registry/registry.json'.
- Boundary markers: There are no instructions or delimiters provided to ensure the agent ignores potentially malicious instructions embedded within the processed UI code or JSON metadata.
- Capability inventory: The skill environment allows for file system modifications and execution of CLI tools like 'npx'.
- Sanitization: The skill does not specify any validation or sanitization logic for data retrieved from the component registry or source files.
Audit Metadata