github.comrepoAgentHound
AgentHound is an open-source offensive security framework that, from a single compromised host, collects local credentials and agent configuration, discovers and fingerprints reachable AI services (MCP servers, A2A agents, model gateways, inference servers like Ollama, vector stores, MLOps platforms, notebooks), reuses harvested credentials to verify concrete access, and writes everything to a checkpointed JSON artifact. An optional analysis server (Neo4j/PostgreSQL-backed) turns the artifact into a queryable attack graph with credential-chain, cross-protocol pivot, exfiltration/execution paths, and prompt-injection-related findings (POISONED_INSTRUCTIONS, POISONED_DESCRIPTION, SHADOWS). It supports an active mode (credential reuse, differential reads, reversible mutation with auto-rollback) and a read-only --stealth mode for OPSEC-constrained engagements.
Technologies named here
- AgentHound
- MCP services
- AgentHound analysis server
- A2A services
- Ollama
- Agent clients
- Model gateways
- ContextForge
- Neo4j
- Inference servers
- Vector stores
- PostgreSQL
- MLOps services
- Docker Compose
- Notebooks
- macOS
- Linux
- Windows
- Model Context Protocol
- Docker
Techniques named here
- Foothold configuration mapping
- Network discovery of AI services
- Service enumeration and inventory
- Credential reuse/expansion
- Access verification
- Evidence preservation
- Attack path graph analysis
- Instruction poisoning / prompt injection detection
- Stealth/read-only collection
- Reversible mutation with recovery
Related in AI Security
blog.talosintelligence.comtoolIntroducing CAIRN: Frontier tracking for AI-integrated malware (Cisco Talos)
github.comadvisoryFlowise MCP Security Bypass Enables RCE
github.comrepoYesWeHack Claude Kit
jfrog.comarticle