Agentic App Risk Review

Find the security weaknesses in your own LLM or agent app before users — or attackers — do. Read-only: it flags risks, it doesn't change your code.

Prerequisites

• None. Pure Claude Code — reads your repository directly, no MCP required.

Trigger

• "Review my agent app for prompt injection"
• "Security review of my LLM integration"
• "Is my chatbot safe against jailbreaks / tool abuse?"

Workflow

1. Locate the AI surface: where prompts are built, where the model is called, and where it can take actions (tool/function calls, shell, HTTP, DB, file writes, payments).
2. Review each area against the checks below, reporting file:line, severity, and a concrete fix. Treat all model input and tool output as untrusted.