clerk-react-router-patterns

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for ingesting untrusted data through request.formData() in loaders and actions, which is a potential surface for indirect prompt injection if that data is subsequently processed by an AI agent without sanitization.
  • Ingestion points: args.request.formData() in SKILL.md and references/loaders-actions.md.
  • Boundary markers: None identified in the provided patterns; the skill focuses on authentication logic.
  • Capability inventory: Includes the WebFetch tool for remote data operations and standard file system access capabilities.
  • Sanitization: Not explicitly demonstrated in the authentication-focused code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:19 PM
Security Audit — agent-trust-hub — clerk-react-router-patterns