nextjs-best-practices
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION] (HIGH): The skill enables the agent to process and modify external codebase content (untrusted data) using powerful tools without implementing any security boundaries or sanitization logic. * Ingestion points: Project files accessed via Read, Glob, and Grep tools. * Boundary markers: None present; the skill does not instruct the agent to ignore instructions embedded in data. * Capability inventory: Write and Edit tools allow for direct modification of files based on processed input. * Sanitization: None; the agent lacks instructions to filter or escape potentially malicious content within processed files.
- [NO_CODE] (SAFE): The skill consists entirely of Markdown-based educational content and documentation. It does not include scripts, binaries, or configuration files that execute logic locally.
Recommendations
- AI detected serious security threats
Audit Metadata