$ loading_
Detects leaked secrets and prompt injections, then redacts text before LLM use.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "classifinder-mcp" yet — see the docs or source repo.
Scan the following ticket text, detect leaked API keys, passwords, tokens, and prompt injection phrases, then return a redacted safe version: {{ticket_text}}Returns detected secrets and injection markers, plus a redacted version safe to send to an LLM.
Before sending these retrieved document chunks to the LLM, check for credentials, internal secrets, or malicious prompt injection content, and produce a cleaned version: {{document_chunks}}Outputs a risk summary and sanitized document chunks ready for the RAG question-answering flow.
Review this text input that will enter an AI workflow, detect sensitive data leaks and override instructions, and replace high-risk content with redaction placeholders: {{input_text}}Provides a safe input version with risk notes that can be passed into downstream AI automation steps.
Scan codebases for LLM usage, AI frameworks, and exposed secrets.
Scan text and URLs for prompt injection risks in AI agents.
Audit MCP configs for exposed access, secrets, models, and compliance AI-BOMs.
Scan prompts locally and redact sensitive data before sending to LLMs.
Automate red-teaming and reliability audits for AI agents through MCP.
Monitor AI inputs and outputs to block injections, leaks, and phishing.