Results for “llm-red-teaming”

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

AI/LLM red-team assessment using the OWASP LLM Top 10 (2025) + OWASP AI Testing Guide (AITG v1, Nov 2025) frameworks, plus OWASP MCP Top 10 runtime testing for agentic/MCP targets. Tests prompt injection, jailbreaks, system prompt leakage, sensitive data extraction, excessive agency, improper output handling, model extraction, content bias, evasion, membership inference, MCP token exposure, MCP command injection, and more. Uses four tools in combination: FuzzyAI (single-turn jailbreak fuzzing), PyRIT (multi-turn orchestrated attacks), Garak (probe-based vulnerability scanning), and promptfoo (plugin-based red-team evaluation). Each tool covers different OWASP categories; running them together gives systematic coverage. Includes a conditional MCP reconnaissance phase and a post-access AI infrastructure phase (chained from /post-exploit). Produces: OWASP LLM Top 10 + AITG + MCP coverage matrix, findings per category, architecture diagram of the AI system, PoCs for confirmed exploits. Chains into /gh-export for

Trains, evaluates, exports, and runs inference for person re-identification models using TAO, learning discriminative embeddings for cross-camera matching.

Defines scope, objectives, rules of engagement, threat model selection, and operational timelines for red team engagements before any offensive testing begins.

Spawns GLM-5 powered teammates with native thinking mode for coding, review, testing, planning, and research tasks.

Spawns GLM-5 powered teammates with thinking mode for coding, review, testing, planning, and research tasks.

Evaluates LLM performance using BLEU, ROUGE metrics and LLM-as-judge. Use for model testing.

Guides project-level decisions for LLM-powered systems: task-model fit, pipeline architecture, token and cost estimation, and agent-assisted iteration.

Expert en tests d'agents IA (tests unitaires, intégration, régression, guardrails, red teaming agents)

P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when coordinating 3+ parallel agents. Produces: Task Prompts (六要素) + P8 team delivery.

Design a lead routing and SLA model someone can actually implement. The assignment rules, the round-robin or account-based logic, the SLA timers, and the fallbacks when a rep is out or a lead has no owner. Built for B2B RevOps teams, customizable to your CRM and your team shape. Trigger on "design lead routing", "who should get this lead", "build our SLA", "round robin rules", "leads are falling through", or any routing diagnostic.

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

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Probe RAG applications for prompt injection via poisoned retrieved context and embedding manipulation.

Automate multi-turn adversarial conversations against LLM agents using Microsoft PyRIT, including Crescendo and Tree-of-Attacks-with-Pruning (TAP) attack chains with scorer feedback loops.