nextjs-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents an attack surface for indirect prompt injection because it is designed to ingest and analyze external source code which could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: The skill uses
glob,grep, andreadtools to access and process Next.js project files such aspage.tsx,layout.tsx,route.ts, andmiddleware.ts(SKILL.md). - Boundary markers: The instructions do not provide specific delimiters for separating code content from instructions, though Instruction 8 includes a validation step to verify findings against the actual code context.
- Capability inventory: The skill environment allows access to
Read,Edit,Grep,Glob, andBashtools, which could be abused if the agent is successfully injected (SKILL.md). - Sanitization: No automated sanitization or filtering of external content is specified; however, the agent is instructed to manually confirm pattern violations and remove false positives as a safeguard (Instruction 8).
Audit Metadata