AI & ML

k-dense-ai Bundle

Guides statistical hypothesis testing with assumption checks, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting for research data.

k-dense-ai Bundle

Formulate testable hypotheses from observations, design experiments, and generate predictions using a structured scientific method framework.

k-dense-ai Bundle

Create publication-quality scientific diagrams using AI generation with smart iterative refinement and quality review.

k-dense-ai Bundle

Integrates with the protocols.io API v3 to search, create, update, and publish scientific protocols, manage steps and materials, handle discussions, organize workspaces, and upload files.

mcollina Bundle

Creates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling quirks, workflow preferences, and project-specific rules that agents cannot infer from reading the codebase.

mcollina Bundle

Handles git and GitHub operations using the gh CLI, triggered by any github.com URL. Covers creating and reviewing PRs, watching CI checks, interactive rebasing, branch cleanup, submodule management, and repository archaeology.

mcollina Bundle

Improves AI skills for activation, clarity, and cross-model reliability through benchmarking, salience tuning, and regression triage.

mcollina Bundle

Designs complex generic types, refactors `any` types to strict alternatives, creates type guards and utility types, and resolves TypeScript compiler errors.

mukul975 Bundle

Run NVIDIA garak probe suites against an LLM endpoint to test for jailbreaks, prompt injection, data leakage, and toxic generation, then interpret the hit-rate report for triage and reporting.

mukul975 Bundle

Model threat actors, intrusion sets, campaigns, and TTPs as a STIX 2.1 knowledge graph in OpenCTI using the pycti Python client, connectors, and import workers for structured cyber threat intelligence.

mukul975 Bundle

Deploy Llama Guard, NeMo Guardrails, and LLM Guard as runtime input/output scanners to block jailbreaks, prompt injection, and toxic content in production LLM applications.

mukul975 Bundle

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

mukul975 Bundle

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.

mukul975 Bundle

Detect model stealing, model inversion, and membership inference performed through inference-API abuse by monitoring query patterns, applying output perturbation, and red-teaming your own model's extractability.

mukul975 Bundle

Detect and defend against prompt injection hidden in documents, web pages, and images consumed by an agent.

mukul975 Bundle

Provides a structured framework for analyzing cyber intrusions by examining four core features: Adversary, Capability, Infrastructure, and Victim. Covers implementing the Diamond Model programmatically to classify and correlate intrusion events, build activity threads, and generate pivot-ready intelligence.

mukul975 Bundle

Test web applications for clickjacking vulnerabilities by assessing frame embedding controls and crafting proof-of-concept overlay attacks during authorized security assessments.

mukul975 Bundle

Apply least-privilege tool allowlisting, identity binding, and human-in-the-loop controls for agent tool calls.

mukul975 Bundle

Deploys and configures CrowdStrike Falcon EDR sensors across Windows, macOS, and Linux endpoints, sets prevention and response policies, validates deployment, and integrates with SIEM platforms.

mukul975 Bundle

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.

mukul975 Bundle

Design and implement security zones and conduits for industrial automation and control systems per IEC 62443-3-2, including zone partitioning, firewall configuration, and validation through traffic analysis and penetration testing.

mukul975 Bundle

Detects command-and-control (C2) communications tunneled through DNS protocol, including DNS tunneling tools, domain generation algorithms, and encoded payload delivery via TXT/CNAME records.

mukul975 Bundle

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

mukul975 Bundle

Extract embedded configuration from Agent Tesla RAT samples including SMTP/FTP/Telegram exfiltration credentials, keylogger settings, and C2 endpoints using .NET decompilation and memory analysis.

mukul975 Bundle

Correlate findings across OSINT sources—username enumeration, email lookups, social media profiles, domain records, breach databases, and dark-web mentions—into unified intelligence profiles with confidence scoring and link analysis.

mukul975 Bundle

Scan Model Context Protocol servers and tool metadata for poisoning, SSRF, and unauthenticated exposure.

mukul975 Bundle

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.

mukul975 Bundle

Design and implement network segmentation in Operational Technology environments using VLANs, industrial firewalls, data diodes, and software-defined networking, following the Purdue Model and IEC 62443 standards.

mukul975 Bundle

Test vector stores for embedding inversion, cross-tenant leakage, and poisoning.

mukul975 Bundle

Implement Microsoft's Enhanced Security Admin Environment (ESAE) tiered administration model for Active Directory, covering Tier 0/1/2 separation, privileged access workstations, and credential theft mitigation.

mukul975 Bundle

Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.

mukul975 Bundle

Conduct comprehensive security assessments of Operational Technology (OT) networks including SCADA systems, DCS architectures, and industrial control system communication paths, addressing the Purdue Reference Model layers and identifying IT/OT convergence risks.

mukul975 Bundle

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

mukul975 Bundle

Deploy and configure Wazuh SIEM/XDR for endpoint detection including agent management, custom decoder and rule XML creation, alert querying via the Wazuh REST API, and automated response actions.

mukul975 Bundle

Design and implement Privileged Access Workstations (PAWs) with device hardening, just-in-time access, and integration with CyberArk or BeyondTrust for secure administrative operations.

mukul975 Bundle

Detects prompt injection attacks targeting LLM-based applications using regex pattern matching, heuristic scoring, and DeBERTa transformer classification.