server-components-design
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes patterns for ingesting untrusted data via request-scoped inputs such as searchParams and params.
- Ingestion points: The skill references params, searchParams, cookies(), and headers() as dynamic inputs in SKILL.md.
- Boundary markers: The skill recommends the use of Data Transfer Objects (DTOs), the server-only package, and React Taint APIs to delimit data boundaries.
- Capability inventory: The skill is restricted to Read and Grep tools.
- Sanitization: The instructions emphasize the need to re-verify session and resource ownership server-side rather than trusting raw request inputs.
Audit Metadata