clerk-authentication
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes code snippets for server actions that ingest external user data, creating a potential surface for indirect prompt injection. Ingestion points: formData parameter in the createPost function within SKILL.md. Boundary markers: Absent; the provided code does not utilize specific delimiters or instructions to prevent the agent from interpreting embedded instructions within the user data. Capability inventory: The skill demonstrates capabilities for database operations (db.post.create) and network requests (fetch) which could be targeted by an injection attack. Sanitization: The examples do not explicitly show input validation or sanitization steps for the external content.
- [EXTERNAL_DOWNLOADS]: The skill references installation of official packages from Clerk, which is a well-known authentication service. Evidence: npm install @clerk/nextjs and @clerk/themes in SKILL.md.
Audit Metadata