nextjs-security-scan

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary purpose is defensive security auditing, and its file access patterns are consistent with this goal.
  • [DATA_EXFILTRATION]: The skill accesses sensitive files like .env to detect credential leakage. This activity is restricted to reading local files for analysis and does not involve network communication or data exfiltration.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by processing untrusted project files. 1. Ingestion points: Next.js project files (app/**, middleware.ts, next.config., .env). 2. Boundary markers: Not present; the agent reads code directly into its context. 3. Capability inventory: Uses Glob, Grep, and Read for analysis; no write or network capabilities are requested. 4. Sanitization: No specific filtering or escaping of ingested file content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 12:44 PM
Security Audit — agent-trust-hub — nextjs-security-scan