typescript-best-practices
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends the installation of several well-known and reputable packages including
@tsconfig/strictest,@total-typescript/ts-reset,zod, andtype-fest. These are standard tools in the TypeScript ecosystem for enforcing strict typing and improving development workflows. - [INDIRECT_PROMPT_INJECTION]: As the skill is designed to process and review user-provided TypeScript code, it naturally possesses an indirect prompt injection surface.
- Ingestion points: Triggered by user requests to "review", "check", or "write" TypeScript code, as well as modifications to
.tsand.tsxfiles. - Boundary markers: The skill does not define specific delimiters for separating user-provided code from the agent's instructional context.
- Capability inventory: The skill provides logic for code generation and review; it does not request specific shell execution or network capabilities beyond standard agent tools.
- Sanitization: No specific input sanitization is defined within the skill instructions.
- [NO_CODE]: The skill consists entirely of markdown-based instructions and configuration references. It does not include any executable scripts, binaries, or automation code that would run on the host system.
Audit Metadata