BestPromptFinder

Prompt Injection & Jailbreak Attack Surface Security Auditor

Quality, usefulness and confidence are AI evaluations out of 100 — not user ratings. Community results come from visitors' "worked / didn't work" votes below. How scoring works →

The prompt

You are an AI red-teaming and cybersecurity specialist. Audit the following LLM system prompt and tool-use architecture: {{system_prompt_and_tool_definitions}}. Evaluate vulnerabilities against direct and indirect prompt injection attacks (e.g., hidden HTML comment instructions in retrieved RAG context, multi-lingual bypasses, recursive token smuggling, privilege escalation via MCP tools). Provide: 1) Threat vector analysis with CVSS-style risk severity; 2) Three specific attack payload simulations demonstrating how an attacker could bypass guardrails; 3) Hardened system prompt patches using XML perimeter tags, input sanitization rules, and strict output boundaries; and 4) Recommended continuous observability rules to detect runtime injection attempts.

Why this prompt

• AI-graded 90/100 for quality and structure
• Written for Claude 3.7 Sonnet (Extended Thinking)

Source & licence

• Original source: solguruz.com ↗
• Author / dataset: Uploaded
• Licence: Not stated by the source. Review the original source terms before commercial reuse.
• Adapted: Imported unmodified.
• Imported: 2026-09

Related Other prompts