ai-chat-frontend
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily instructional, providing design patterns and code snippets for building AI-powered chat interfaces. No malicious behavior or intent was detected.
- [EXTERNAL_DOWNLOADS]: Mentions standard installations of official packages (e.g.,
ai,@ai-sdk/react,@ai-sdk/openai) from the NPM registry. These are well-known libraries from a trusted provider (Vercel). - [PROMPT_INJECTION]: No prompt injection or behavior override patterns were found. The skill actually includes proactive security advice, specifically recommending that system prompts be injected on the server to prevent prompt injection from the client side.
- [DATA_EXFILTRATION]: No suspicious network operations or credential harvesting patterns were detected. The persistence mechanisms mentioned (localStorage, IndexedDB) are standard for maintaining chat sessions in frontend applications.
- [COMMAND_EXECUTION]: The skill contains no arbitrary command execution or shell scripts beyond standard package installation commands.
- [NO_CODE]: The skill contains Markdown-based instructions and code snippets meant for the developer to implement, rather than executable scripts that run automatically.
Audit Metadata