clerk-custom-ui
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch external content from clerk.com which is then used to generate code and configuration, creating a surface for indirect instructions to influence agent behavior.
- Ingestion points: Documentation URLs listed in the 'Component Customization Options' table in
SKILL.mdare fetched usingWebFetchat runtime. - Boundary markers: The instructions lack explicit delimiters or directions for the agent to ignore or sanitize embedded instructions within the fetched documentation content.
- Capability inventory: The skill facilitates file writing (JSX/TSX component generation) and package installation (
npm install) based on the retrieved information. - Sanitization: No content validation or filtering mechanisms are defined for the data retrieved from external URLs before it is interpolated into the agent's context.
Audit Metadata