Results for “moltguard”

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Guides AI agents to apply advanced mathematical and probabilistic techniques (Bloom filters, HyperLogLog, FFT, etc.) for large-scale data problems where classical algorithms are optimal but math offers better asymptotic bounds.

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.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

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.

Deploy Meta's LlamaGuard moderation model to filter LLM inputs and outputs across 6 safety categories using HuggingFace, vLLM, or FastAPI.

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.

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.

Interact with Moltbook social network for AI agents. Post, reply, browse, and analyze engagement. Use when the user wants to engage with Moltbook, check their feed, reply to posts, or track their activity on the agent social network.

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

Bootstraps AGENTS.md and CLAUDE.md for AEM 6.5 LTS projects, tailored to project structure and detected add-ons.

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

Engage with a social platform for AI agents: post text, photos, quotes, links, and chat logs; reblog with commentary; tag content; follow agents; send and answer asks; and manage your profile via a CLI tool.

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Assigns behavioral trust grades (A–F) to MCP servers by running probes for prompt injection, permission overreach, data leaks, and adversarial-input handling, and publishes reproducible onchain attestations.

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

Sets up MQTT brokers and clients for messaging in IoT systems. Use for lightweight messaging in IoT.

Imported skill utils from langchain

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Featurização molecular para ML (100+ featurizadores). ECFP, MACCS, descritores, modelos pré-treinados (ChemBERTa), converter SMILES em features, para QSAR e ML molecular.

Enables AI agents to post, reblog, tag, and interact on the moltr social platform via a CLI tool, with feeds, discovery, asks, and profile management.

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

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Convert chemical structures (SMILES or RDKit molecules) into numerical representations for machine learning, covering 100+ featurizers including ECFP, MACCS, descriptors, and pretrained models like ChemBERTa, with support for QSAR modeling and virtual screening.

Validate monorepo lane specs before dispatch and verify integrated changes stay inside declared lane boundaries

Crafts and sends personality-rich promotional messages to the Moltbook audience.

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Scans local repos and AI agent skill folders for security drift, saves trusted baselines, and compares changes after updates to highlight risky new capabilities.

Provides Vue Router 4 patterns, navigation guards, route params, and route-component lifecycle interactions.

Configure Cedar policy enforcement and Ed25519 signed receipts for Claude Code tool calls. Use when setting up projects that need cryptographic audit trails, policy-gated tool execution, or compliance-ready evidence of agent actions.

Enforces a read-only rule for filesystem junctions and symlinks, blocking writes, deletes, and git commits that resolve outside the current project root.

Enumerate Microsoft Entra ID tenants using ROADrecon and acquire/exchange tokens with roadtx for authorized red-team operations.

Build lightweight AI agents with HuggingFace Smolagents — use CodeAgent (writes Python to act) or ToolCallingAgent (JSON tool calls), add built-in or custom Tools, orchestrate multi-agent pipelines with ManagedAgent, and run locally or via HF Inference API.

Set up, run, and contribute to TokHub (github.com/yaojingang/TokHub) — an open-source AI API relay monitoring, recommendation, and OpenAI-compatible gateway system with L1/L2/L3 channel health probing, usage metering, alerts, audit, and Docker self-hosting. Use when the user asks about TokHub, "AI API 中转站监控", cloning/running the Go + React monorepo (TOKHUB_ROLE, sqlc, TimescaleDB, NATS), the L1/L2/L3 probe algorithm, the OpenAI-compatible `/gateway/v1/*` endpoint, or contributing a PR to TokHub. Do not use for connecting a running agent to a live TokHub instance's own API (that is covered by the project's own bundled `agent-skills/tokhub` skill inside the TokHub repo, not this one).

Simulates man-in-the-middle attacks using Ettercap, mitmproxy, and Bettercap in authorized environments to intercept, analyze, and modify network traffic for testing encryption enforcement, certificate validation, and detection capabilities.