Agent building

Analyze Chromium-based browser artifacts using Hindsight to extract browsing history, downloads, cookies, cached content, autofill data, saved passwords, and…

Detect and analyze Linux persistence mechanisms including crontab entries, systemd service units, LD_PRELOAD hijacking, bashrc modifications, and…

Detect PowerShell Empire framework artifacts in Windows event logs by identifying Base64 encoded launcher patterns, default user agents, staging URL…

Identify ransomware network indicators including C2 beaconing patterns, TOR exit node connections, data exfiltration flows, and encryption key exchange via…

Build a systematic threat hunt hypothesis framework that transforms threat intelligence, attack patterns, and environmental data into testable hunting…

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…

Systematically deobfuscate multi-layer PowerShell malware using AST analysis, dynamic tracing, and tools like PSDecode and PowerDecode to reveal hidden…

Detect DCSync attacks where adversaries abuse Active Directory replication privileges to extract password hashes by monitoring for non-domain-controller…

Visual dashboard for your OpenClaw agent.

Build recoverable Anvia workflows with @anvia/durable — durable main agents, owned subagents, task graphs, tool/effect recovery, persisted waits, and remote…

AI agent memory with mathematical foundations.

Guide for creating high-quality Model Context Protocol (MCP) servers and tools.

Secure key management for AI agents.

Security scanner for AgentSkill packages.

Validates all CI skills in this repo.

Use for GEPA reflective optimization, ReAct agent optimization, feedback metrics, LLM reflection, and execution trajectories.

Use for MCP tools with DSPy, Model Context Protocol servers, dspy.Tool.from_mcp_tool, and ReAct agents over MCP-compatible tools.

Use for GEPA optimize_anything on text artifacts such as code, prompts, agent architectures, configs, and non-DSPy optimization targets.

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

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

Generate log2timeline and Plaso super-timelines and triage them in Timesketch.

Deploy Llama Guard, NeMo Guardrails, and LLM Guard input/output scanners as runtime defenses.

Identify poisoned training data and backdoored models across the ML pipeline.

Build Anvia agents and tools — Agent options, tool definitions, approvals, memory, streaming, multi-agent teams, and provider wiring.