v1.2.0: Autonomous Red Teaming Update

Release v1.2.0: Autonomous Red Teaming Update

This release transforms Gideon from a defensive intelligence analyst into a Dual-Mode Autonomous Security Platform, introducing safe, sandboxed offensive capabilities alongside our existing defensive guardrails.

What's New

🛡️ Dual-Mode Architecture

• Red Team Mode: Added the /redteam command to unlock authorized autonomous exploitation with strict engagement scoping limits.
• Dynamic Guardrails: NeMo Guardrails now dynamically unload when transitioning to Red Team mode to permit offensive workflows.

⚡ Action Engine & Sandboxing

• Introduced Docker-based Execution Sandboxes for all external tools executed by the LLM (like nmap, nuclei, sqlmap, metasploit) to guarantee host safety.
• Built a command orchestration engine that autonomously parses stdout/stderr vulnerability findings and injects them directly into the Neo4j intelligence graph.

📡 C2 Framework Interoperability

• Added a unified C2 interface adapter system for persistent session management.
• Implemented native gRPC support for the Sliver C2 framework, enabling Gideon to locally list sessions, deploy stagers, and execute commands through active implant beacons.

🛠️ Expanded Offensive Skills

• Weaponization: Added an autonomous payload generator leveraging msfvenom to build, encode, and obfuscate payload loaders for EDR evasion.
• Post-Exploitation: Integrated Active Directory network mapping into the graph database, powering an intelligent lateral movement decision engine for privilege escalation tracking.

🔐 OpenClaw Sentinel Integration

• Released fully updated configuration models and documentation for OpenClaw Sentinel (acting as an AI-powered WAF and sidecar).

🐛 Bug Fixes & Chore

• Resolved all pre-existing TypeScript compilation errors (@types) and implicit any traces across the graph, engine, openclaw, and mcp subsystems.
• Synchronized missing dependencies in package.json and updated the docs/ sidebar navigation.

Full Changelog: v1.1.1...v1.2.0

v1.1.1: TypeScript Error Resolution

Fixed

• Strict Type Safety Enforcement: Resolved ~80 TypeScript compilation errors to achieve successful compilation via tsc --noEmit.
• Barrel File Re-exports (src/gideon/index.ts):
  • Updated re-exports from prompts.ts, recon.ts, and reports.ts.
  • Replaced non-existent exports (e.g., buildReportPrompt, formatHackerOneReport) with actual implementations (like buildStatusPrompt, generateEngagementReport).
• Zod v4 API Compatibility:
  • Updated z.record(z.any()) schemas to z.record(z.string(), z.any()) ensuring compliance with v4 schema definitions.
  • Removed explicit empty object assignments .default({}) for properties with required fields to fix parameter overload mismatch errors across governance/types.ts, openclaw/types.ts, skills/types.ts, tools/security/types.ts, and utils/config-loader.ts.
• Skills Layer Refactoring: Fixed staleness by aligning references with current underlying internal APIs.
  • Code Scanning: Migrated logic to scanPath from deprecated scanDirectory, updating internal result field mappings.
  • Data Analytics: Updated deprecated runBatchIOCAnalysis calls to batchAnalyzeIOCs, alongside modern RapidsResult fields.
  • Governance: Standardized proxy entity property access (e.g., createdAt -> registeredAt, lastActiveAt -> lastSeenAt) and properly invoked AuditLogger.listPolicySets.
  • Security Research: Realigned missing toolkit functions (getToolsByCategory) and updated missing enumeration fallback hooks.
  • Threat Detection: Updated commands to modern Morpheus GPU pipeline wrappers (analyzeWithDFP, detectDGA, detectPhishing, detectRansomware).
  • Voice: Remapped speakText invocation footprint to match the textToSpeech generalized parameterized options dictionary format.
• Null-Safety & Casting Validations:
  • gideon.ts: Re-aligned parameter properties for accurately calculating CVSSInput.
  • rapids.ts: Eliminated compilation type-casting violations across operations by using safe intermediaries (as unknown as Type).
  • agent-registry.ts: Corrected potential truthy syntax leaks utilizing strict conditional object spreading.
  • credential-guard.ts & personaplex.ts: Installed exact strict null and undefined bounding criteria for WebSocket connections and active session handling properties.
  • scanner.ts: Deduped recursive object properties initialized within native code configurations.

v1.1.0

What's Changed

• feat: integrate OpenRouter and fix Tavily lazy initialization by @requie in #5
• Merge Dev with main for resync by @requie in #6
• Merge pull request #6 from Cogensec/main by @requie in #7
• docs: Update README to detail new Exa AI, OpenRouter, and NVIDIA integration by @requie in #8
• docs: Add new feature documentation and install project dependencies. by @requie in #9
• chore: Update Netlify build command to nest build output under `dist/… by @requie in #10
• feat: initialize Astro Starlight documentation site with custom brand… by @requie in #11
• Dev by @requie in #13
• Feat openclaw security sidecar by @requie in #14

Full Changelog: https://github.com/Cogensec/Gideon/commits/v1.1.0