Results for “prompt-guard”

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Generates custom safety policies for NVIDIA Nemotron content-safety guardrails, producing a Markdown policy, JSON taxonomy, and inference prompts from rough user input.

Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.

Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.

Full safety mode: destructive command warnings + directory-scoped edits. (gstack)

Full safety mode: destructive command warnings + directory-scoped edits. (gstack)

Generates optimized prompts for any AI tool. Use when writing, fixing, improving, or adapting a prompt for LLM, Cursor, Midjourney, image AI, video AI, coding agents, or any other AI tool.

Expert prompt optimization system for the prompts INSIDE an AI product you are building — system prompts, LLM feature prompts, chatbot/agent instructions. Use when the user wants to write or improve a system prompt for an AI feature they're shipping, review/critique an LLM prompt, apply prompt-engineering techniques (chain-of-thought, few-shot, structured output, hard constraints) to a product prompt, or optimize cost/latency of a production prompt. Do NOT use this to clarify or structure the user's own vague request to Claude Code — that is `prompt-clarifier`'s job, not this skill's.

Resolves legacy references to the security-guardian capability by routing to the current runtime equivalent.

Prevents destructive operations on production systems and restricts file edits to a specific directory when running agents autonomously.

Assess AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, and agent tool abuse, with MITRE ATLAS mapping and guardrail recommendations.

Prevents destructive operations on production systems and restricts edits to a specified directory when running agents autonomously.

Full safety mode: destructive command warnings + directory-scoped edits. (gstack)

Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.

Use this skill to prevent destructive operations when working on production systems or running agents autonomously.

Runs before every git commit on heleni-memory. Checks: no credentials in tracked files, no oversized files, valid SKILL.md frontmatter for any new/modified skill. Triggers: "commit", "before push", "validate repo", or auto-runs as a git pre-commit hook.

Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.

Designs, optimizes, and evaluates prompts for LLMs, including structured outputs, chain-of-thought, and evaluation frameworks.

Prevents destructive operations when working on production systems or running agents autonomously by intercepting risky commands and restricting file edits to a specified directory.

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

Security controls for RAG. Indirect prompt-injection via retrieved documents, PII detection/redaction (Microsoft Presidio, AWS Comprehend), multi-tenant isolation, ACL-aware retrieval with row-level/metadata filtering, data-leakage prevention, jailbreak hardening on retrieved context, GDPR right-to-be-forgotten in vector DBs. USE WHEN: user mentions "prompt injection RAG", "indirect prompt injection", "PII redaction", "Presidio", "ACL RAG", "row-level security", "multi-tenant RAG isolation", "GDPR vector DB", "right to be forgotten", "jailbreak", "data leakage RAG" DO NOT USE FOR: hallucination detection - use `rag-guardrails`; tenancy scaling patterns - use `rag-production`; audit tracing schema - use `rag-observability`

Expert prompt optimization for LLMs and AI systems. Use PROACTIVELY when building AI features, improving agent performance, or crafting system prompts. Masters prompt patterns and techniques.

Review docs, tool output, skills, and memory candidates for prompt-injection risk.

Turn a rough task into a precise, ready-to-paste prompt for any AI platform (Claude, GPT, Gemini, and others). Trigger on "write me a prompt for", "I need an AI to", "help me prompt engineer", "build a system prompt", "make this prompt better", "optimize my prompt", or any prompt-building request.

Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates with evals.

Estrutura prompts para geradores de imagem e vídeo, otimizando custo e consistência com a marca.

Learn and apply prompt engineering techniques for LLMs, image generators, and video models using the inference.sh CLI.

Blocks Edit/Write/Bash actions until the agent presents concrete facts about imports, data schemas, and the user's instruction, improving output quality.

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

Forces AI agents to investigate before editing or running destructive commands, improving code quality by requiring concrete facts like importers, data schemas, and user instructions.