ui-design
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow requires the agent to execute shell commands for linting, testing, and building the project (Step 5), as well as performing package upgrades for security patches (Step 0). This grants the agent the ability to trigger scripts defined in the project configuration.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection via the implementation brief and external component inspiration. Ingestion points: user brief (Step 1) and 21st.dev inspiration (Step 3). Boundary markers: Absent. Capability inventory: file system writes and shell command execution. Sanitization: Absent.
- [EXTERNAL_DOWNLOADS]: The skill uses 21st.dev for targeted UI component inspiration and requires screenshot capture capabilities to reference external designs.
Audit Metadata