clerk-setup
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to fetch external documentation and follow the extracted instructions to modify the project environment.
- Ingestion points: The skill utilizes
WebFetchto retrieve content from official documentation URLs onclerk.com(e.g.,https://clerk.com/docs/nextjs/getting-started/quickstart). - Boundary markers: There are no explicit boundary markers or instructions telling the agent to treat the fetched content as untrusted or to disregard potential malicious instructions embedded within the documentation.
- Capability inventory: The skill allows the agent to perform high-privilege actions including package installation (
npm install), file system writes (creating middleware and configuration files), and shell command execution (via theclerkCLI tool). - Sanitization: The skill lacks sanitization or validation mechanisms to verify the integrity of the fetched instructions before the agent executes them.
Audit Metadata