Results for “llm-red-teaming”

Designing red team attack scenarios, threat models, MITRE ATT&CK/OWASP application, Purple Team exercises, and AI/LLM red teaming. Use when adversarial security validation is needed.

Executes Atomic Red Team tests mapped to MITRE ATT&CK techniques, performs coverage gap analysis, and runs detection validation loops to measure blue team visibility.

Coordinates purple team exercises by running MITRE ATT&CK-mapped attack scenarios with real-time detection testing and collaborative gap remediation.

Plan and execute a comprehensive red team engagement covering reconnaissance through post-exploitation using MITRE ATT&CK-aligned TTPs to evaluate an organization's detection and response capabilities.

Find adjacent vendors and subs (not top market primes) who fill a capability gap against a displacement target using USASpending flows and SAM entity signals. Use when user defines a teaming gap and wants vault-ready partner shortlist with citations.

Generates a single-frame HTML template with a cinematic film-leak aesthetic: warm light leaks, 35mm grain, 2.39:1 letterbox, and serif typography for opening titles or chapter cards.

Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.

Executes Atomic Red Team tests for MITRE ATT&CK technique validation using the atomic-operator Python framework. Loads test definitions from YAML atomics, runs attack simulations, and validates detection coverage.

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

Plan and execute authorized red team engagements with structured attack path analysis, MITRE ATT&CK kill-chain planning, technique scoring, choke point identification, OPSEC risk assessment, and crown jewel targeting.

Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved environment.

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

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

Detects lateral movement techniques including Pass-the-Hash, PsExec, WMI execution, RDP pivoting, and SMB-based spreading using SIEM correlation of Windows event logs, network flow data, and endpoint telemetry mapped to MITRE ATT&CK Lateral Movement (TA0008) techniques.

Simulates real-world adversary operations to test an organization's detection and response capabilities through the full attack lifecycle, from reconnaissance to objective completion.

Run a cross-division all-hands meeting that includes both AI Lab and AI Startup agents. Use when the user requests to "start an all-hands", "convene both divisions", or "run a cross-division meeting".

Layer 4 of the keyword research pipeline. Spawns a "skeptical SEO" adversarial sub-agent to argue against every survivor of Layers 1-3. Catches mechanical-classifier blind spots — wrong SERP intent, hidden link-graph gauntlets, AIO trajectory shifts, vanity-rank metrics. Same pattern as quality-check's adversarial draft read, applied to keyword selection.

Automate red team operations using the Covenant C2 framework's REST API for authorized adversary simulation, including listener setup, grunt deployment, task execution, and lateral movement tracking.

Creates safety alert decks with hazard stripes, tiered cards, and policy code blocks for incident reviews and risk communication.

Adversarial red-team of a running web, React Native, or Capacitor hybrid app. Use when asked to "red team this app", "attack my app", "break it", "find all the defects", "adversarial test", "pre-launch hardening", "pentest the app", or "full app QA". Naive monkey / guest vs logged-in wander → test-exploratory.

Red-team a PRD, roadmap, or strategy by attacking its load-bearing assumptions before reality does, ranking failure modes by impact, likelihood, and cheapness to test.

Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.

CLI-team runtime for claude, codex, gemini, antigravity, grok, or cursor workers in tmux panes when you need process-based parallel execution

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

Wilkinson, branchline, ratrace, directional couplers, corporate dividers, Rotman lenses for power splitting and beam-forming. TRIGGER: user asks to design, create, or analyze any coupler, splitter, power divider, combiner, or Rotman lens. Invoke BEFORE writing code — class names and design() availability vary per coupler type. SKIP: EM simulation/S-parameter extraction of an existing component (use matlab-analyze-em), building custom non-catalog geometry (use matlab-assemble-pcb-layout), material/stackup setup only (use matlab-manage-pcb-material), cascading multiple components (use matlab-integrate-pcb-circuit).

Multi-tiered memory management (HOT/WARM/COLD) for context compaction. Invoke ONLY for explicit compaction events: post-`/compact` cleanup, MEMORY.md tier promotion, archive batch, or "trim my context". NOT for general recall (use deep-recall) or routine memory writes (use storage-router). Triggers: "compact memory", "promote to durable", "archive old context", "tier this".

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

Use when a feature's screens and flows are drafted and the design phase needs a navigable wireframe — a multi-screen greyscale Astro prototype where buttons and links actually work, suitable for the design gate and moderated user testing. In the A-Team pipeline it is conducted by ateam-design and consumes design.md's

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.

Finds, scores, and reaches high-value contacts through social graph analysis and warm path discovery, generating personalized outreach drafts for email, LinkedIn, and X.

This skill should be used when the user asks to "follow red team methodology", "perform bug bounty hunting", "automate reconnaissance", "hunt for XSS vulnerabilities", "enumerate subdomains", or needs security researcher techniques and tool configurations from top bug bounty hunters.