Results for “llm-safety”

Bypasses safety filters on API-served LLMs using jailbreak templates, input obfuscation, and multi-model racing.

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution on local Docker, Slurm HPC, or cloud platforms.

Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

Orchestrator for the eval-output skill suite — evaluate LLM and agent outputs for quality, accuracy, helpfulness, and safety using structured rubrics and LLM-as-judge techniques. Load when the user says "evaluate this output", "score this response", "run an eval", "LLM as judge", "evaluate agent output", "how good is this response", "rate this answer", "eval this", or provides an LLM output that should be assessed for quality. Single entry point for all output evaluation workflows.

Comprehensive LLM security testing prompts for bias detection, data leakage, alignment testing, and adversarial prompt resistance.

Conduct authorized security assessments of LLM applications and AI agents, covering prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.

Read-only OWASP LLM Top 10 audit of app-facing AI features: prompt injection, data leak, supply chain, poisoning, unsafe output, excessive agency, system-prompt leak, RAG/embedding risks, misinformation, unbounded consumption. Use when "audit LLM security", "prompt injection", "jailbreak my chatbot", "is my AI safe".

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Enforces production-grade Python and AI engineering standards for FastAPI, LangChain/LangGraph, RAG pipelines, and LLM integrations, covering type safety, error handling, testing, and security.

Builds input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs using NeMo Guardrails, Presidio, and Guardrails AI.

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.

OWASP Top 10 + Supabase-first hardening burndown. Use when "security audit plan", "OWASP audit", "hardening plan", or "security burndown". App-layer auth flows → audit-auth-flows. Table RLS → plan-rls-audit. Key rotation → plan-secrets-audit. App LLM attacks → audit-llm-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.

Test LLM applications for system prompt leakage using manual payloads, garak, and Promptfoo to extract embedded secrets and routing logic.

Secure Laravel applications with best practices for authentication, authorization, Eloquent safety, CSRF, XSS prevention, API security, and deployment configurations.

Run the Legal Builder Hub security-review gate on a candidate legal skill — inspect its manifest and body for unsafe behavior before any install is allowed.

Detect NTLM relay attacks through Windows Security Event correlation by analyzing Event 4624 LogonType 3 for IP-to-hostname mismatches, identifying Responder/LLMNR poisoning artifacts, and auditing SMB and LDAP signing enforcement.

Detect NTLM relay attacks by analyzing Windows Event 4624 logon type 3 with NTLMSSP authentication, identifying IP-to-hostname mismatches, Responder traffic signatures, SMB signing status, and suspicious authentication patterns across the domain.

Provides a security checklist and hardened code examples for Solidity AMM contracts, covering reentrancy, donation attacks, oracle manipulation, slippage, and admin controls.

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.

Provides expertise in Langfuse for LLM observability, including tracing, prompt management, evaluation, and integration with LangChain, LlamaIndex, and OpenAI.

Detect abuse of legitimate Windows binaries (LOLBins) like certutil, regsvr32, mshta, and rundll32 using process telemetry, Sigma rules, and parent-child process analysis.

Security Craft

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Static OWASP review of app code (injection, headers, deps). Use when "review security" or "check vulnerabilities". Session/route×gate/getSession → audit-auth-flows. Plan-only burndown → plan-security-audit. Table RLS → plan-rls-audit. LLM attacks → audit-llm-security.

Provisions free LLM API keys from 20+ providers, health-checks existing keys, opens signup pages, validates new keys, and saves them to your project.

Guides secure design and review of Lightning Web Components, covering DOM safety, Apex data exposure, and Lightning Web Security.