pick-ui-library
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection by processing external data to perform actions. * Ingestion points: The skill ingests user-provided task descriptions (e.g., "I need toasts") and project configuration data from the local
package.jsonfile. * Boundary markers: There are no explicit delimiters or instructions to the agent to ignore potentially malicious instructions embedded in the user's task description. * Capability inventory: Based on the recommendation, the agent is instructed to install dependencies and modify source code to integrate the chosen libraries. * Sanitization: The skill does not define any sanitization or validation logic for the input strings. - [SAFE]: The curated list contains links to well-known, reputable open-source projects and official documentation. The domain
sonner.emilkowal.skiis identified as a vendor-owned resource corresponding to the authoremilkowalski.
Audit Metadata