15 skills · sorted by relevance
Assessing privacy risks in large language model outputs including training data memorisation, PII leakage in generated text, prompt injection leading to data extraction, and hallucinated personal data. Covers output filtering, guardrails, and monitoring. Keywords: LLM privacy, output risk, memorisation, PII leakage, prompt injection, hallucinated PII.
The English summary is being prepared. Showing the original description.
Configure safety checks for LLM applications with NeMo Guardrails. Covers attempts to bypass safety rules, input and output validation, masking personal information, and checking factual claims through programmable rules and integrations.
Prepare training datasets for large language models with GPU-assisted cleaning. Covers duplicate removal, quality filtering, and personal information redaction, with workflows for text, images, video, and audio using NeMo Curator.
Prepare training datasets for large language models with GPU-assisted cleaning. Covers duplicate removal, quality filtering, and personal information redaction, with workflows for text, images, video, and audio using NeMo Curator.
Add safety checks to LLM applications with NeMo Guardrails. This skill guides input and output validation, detection of attempts to bypass safety rules, personal information masking, and checks for unsupported or inaccurate answers.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
The English summary is being prepared. Showing the original description.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
The English summary is being prepared. Showing the original description.
Prepare LLM training datasets with NeMo Curator by removing duplicates, filtering low-quality content, and redacting personal information. The skill also covers image, video, and audio curation, including GPU processing and distributed workflows.
Plan security controls for LLM applications and AI agents, covering malicious instructions, data leakage, model tampering, and API access. Includes guidance and code examples for filtering outputs, enforcing permissions, isolating networks, and recording audit events.
Framework de segurança em runtime da NVIDIA para aplicações LLM. Com detecção de jailbreak, validação de entrada/saída, verificação de fatos, detecção de alucinações, filtragem de PII, detecção de toxicidade. Usa DSL Colang 2.0 para rails programáveis. Pronto para produção, executa em GPU T4.
The English summary is being prepared. Showing the original description.
Curação de dados acelerada por GPU para treinamento de LLM. Suporta texto/imagem/vídeo/áudio. Recursos incluem deduplicação fuzzy (16× mais rápida), filtragem de qualidade (30+ heurísticas), deduplicação semântica, redação de PII, detecção NSFW. Escala em GPUs com RAPIDS. Use para preparar datasets de treinamento de alta qualidade, limpar dados web ou deduplicar grandes corpora.
The English summary is being prepared. Showing the original description.
Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII Tespit and content policy enforcement, and the Guardrails AI framework for structured output validation. The guardrails system intercepts both user inputs (blocking injection attempts, stripping PII, ...
The English summary is being prepared. Showing the original description.
Tests APIs for excessive data exposure where endpoints return more data than the client application needs, relying on the frontend to filter sensitive fields. The tester intercepts API responses and analyzes them for leaked PII, internal identifiers, debug information, or sensitive business data that the UI does not display but the API transmits. This maps to OWASP API3:2023 Broken Object Property Level Authorization. Activates for requests involving API data leakage testing, excessive data exposure, response filtering bypass, or API over-fetching.
The English summary is being prepared. Showing the original description.
Use this skill when an agent needs AssemblyAI for speech-to-text or speech-understanding work in media production, including pre-recorded, synchronous short-file, and real-time streaming transcription; speaker diarization or speaker identification; captions and subtitles; timestamps; language detection, code-switching, or transcript translation; audio intelligence such as summaries, chapters, topics, entities, key phrases, sentiment, content moderation, profanity filtering, and PII redaction; webhooks, scaling, rate limits, retention, security, consent, and QA for podcasts, interviews, captions, call recordings, and edit workflows.
The English summary is being prepared. Showing the original description.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
The English summary is being prepared. Showing the original description.