reviewing-nextjs-16-patterns
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (SAFE): No patterns of direct instructional override or system prompt extraction were detected in the skill instructions.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or network-based exfiltration triggers are present within the markdown or logic.
- [Remote Code Execution] (SAFE): Suggested commands such as
npm run buildare provided for verification and are not automatically executed by the skill itself. - [Indirect Prompt Injection] (LOW): The skill's primary function involves analyzing untrusted source code, which creates a surface for indirect instructions to influence the agent.
- Ingestion points: Untrusted local source code accessed via
Read,Glob, andGreptools. - Boundary markers: Analysis is scoped to specific Next.js file patterns and extensions, though explicit markers for the LLM are absent.
- Capability inventory:
Read,Glob,Grep, andTodoWritetools are permitted. - Sanitization: There is no explicit sanitization or instruction to ignore embedded prompts in the analyzed code content.
Audit Metadata