BestPromptFinder
Prompt Injection & Jailbreak Attack Surface Security Auditor
90AI Quality /100
89AI Usefulness est. /100
85Eval Confidence /100
No votes yetCommunity results
The prompt
As 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.
Find similar in the app →
Did this prompt work for you?
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: Wording lightly edited by BestPromptFinder (2026-10-13).
- Imported: 2026-09
Related Other prompts
Accessibility Audit Checklist Writer for Web UIsQuality 95 · Claude, GeminiExplain a Kundli Without Predicting the Future
Quality 85 · ChatGPT, GeminiAgentic Goal Alignment & Adversarial Guardrail Enforcer
Quality 81 · DeepSeek-R1Dynamic Recipe Generator from Available Ingredients
Quality 74 · GPT-5.6Language Detector
Quality 70 · Claude, GeminiAnagram Prompt List
Quality 68 · General