adithyan-ak / AgentHound
Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.
Why this job: topics: security-tools, ai-security, llm-security, pentesting, red-team
What it does
The default scan is active because foothold access may disappear at any moment. --stealth switches the same workflow to read-only collection when OPSEC requires it.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 59 days ago
- Stars
- 462
- +3 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- 3 systems
- Mac, Windows, Linux
- Latest version
- 1.1.1
- Released 2 months ago
- Built with
- Go
- 77% of the code
Is it looked after?
- Contributors
- 2
- Last 90 days
- Issues
- 83% closed
- 2 still open
- Pull requests
- 133 merged
- 27 waiting
- Releases
- 3
- 3 in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| 0xSteph / pentest-ai-agents | 2,428 | 2 months ago | MIT | No downloads |
| ASCIT31 / Dark-Moon | 1,211 | 13 days ago | GPL-3.0 | No downloads |
| S1N6H / pentest-harness | 462 | 59 days ago | MIT | No downloads |
More: download files, languages, topics and project record
Download files, 1.1.1
- Mac8 files, 92 downloads
- Windows8 files, 99 downloads
- Linux8 files, 189 downloads
Languages
- Go 77%
- TypeScript 20%
- Shell 2%
- Python <1%
Topics
- a2a
- agentic-ai
- ai-agents
- ai-security
- attack-paths
- bloodhound
- llm-security
- mcp
- model-context-protocol
- neo4j
- offensive-security
- pentesting
Project record
- JobAI security
- StatusListed
- Commits453
- Forks86
- Watching2
- Stars in 28 days+15
- CreatedApr 5, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026