design
Warn
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is instructed to run
bash ../../scripts/check-update.shduring its execution flow. This command executes a shell script located at a relative path outside of the skill's own directory. - [REMOTE_CODE_EXECUTION]: The skill references and encourages the use of
npx getdesign@latest, which downloads and executes a package from the npm registry. The associated projectVoltAgent/awesome-design-mdis an external third-party source not belonging to the skill author or a trusted vendor. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content, including screenshots and source code from repository URLs, which constitutes an attack surface for indirect prompt injection.
- Ingestion points: User-provided screenshots, repository URLs, and pasted source code (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or warnings to isolate these external inputs from the agent's core instructions.
- Capability inventory: The skill utilizes shell command execution (
bash,npx) and performs file system operations (reading source code, theme files). - Sanitization: No explicit sanitization, validation, or filtering is mentioned for the external content before it is processed by the agent.
Audit Metadata