AgentHound AI Agent by Telefonica

by Telefonica• 17•• Scanned•Claim this listing•Request removal
Research & Analysisagentic aiai securityattack path analysisblackhat arsenalbloodhound

BloodHound-style risk analysis for multi-agent AI architectures. Parses CrewAI, Dify, LangGraph, or generic YAML into a typed capability graph and detects reachable attack paths from untrusted input to sensitive data or external action, with live control simulation.

AgentHound is an open-source ai agent by Telefonica, written mainly in TypeScript, with 17 GitHub stars and the AGPL-3.0 license. Its code was last updated Jul 22, 2026.

Scan summary: scanned Nov 5, 2026 at commit 756012f. No capabilities flagged by our checks. Scan policy

What AgentHound can touch

  • Run shell commandsNot seen in this scan
  • Run dynamic codeNot seen in this scan
  • Read or write filesNot seen in this scan
  • Read environment and secretsNot seen in this scan
  • Control a web browserNot seen in this scan
  • Connect to databasesNot seen in this scan
  • Read or send messagesNot seen in this scan
  • Touch money or tradingNot seen in this scan
  • Connect to the internetNot run in this scan

"Not seen" means our checks did not find it, and the tool may still do it. Covers commit 756012f, Nov 5, 2026. See the scan policy.

Before you install AgentHound

AgenticMart scanned AgentHound on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.

What it can access

  • An AI agent decides its own next steps and calls whatever tools you give it, so its risk depends on the access you grant.

Before you install

  1. Pin the version you reviewed instead of always installing the latest release.
  2. Read the tool list or scripts before the first run, and keep approval prompts on for actions that write, send or delete.
  • Maintained by Telefonica on GitHub, 17 stars and 5 forks. Popularity is not proof of safety.
  • Last code change: Jul 22, 2026.
  • Open-source license: AGPL-3.0.

AgentHound is an open-source ai agent by Telefonica, written mainly in TypeScript. BloodHound-style risk analysis for multi-agent AI architectures. Parses CrewAI, Dify, LangGraph, or generic YAML into a typed capability graph and detects reachable attack paths from untrusted input to sensitive data or external action, with live control simulation.

At a glance

Stars
17
Forks
5
Language
TypeScript
License
AGPL-3.0
Created
Jul 2026
Last update
Jul 22, 2026
Type
AI Agent
Price
Free

Topics

agentic-aiai-securityattack-path-analysisblackhat-arsenalbloodhoundcrewaidifyfastapilanggraphllm-securitymulti-agent-systemsnextjsorg-cdoowaspprompt-injectionpublicthreat-modeling

Questions about AgentHound

What is AgentHound?

BloodHound-style risk analysis for multi-agent AI architectures. Parses CrewAI, Dify, LangGraph, or generic YAML into a typed capability graph and detects reachable attack paths from untrusted input to sensitive data or external action, with live control simulation.

Who maintains AgentHound?

AgentHound is maintained by Telefonica on GitHub (Telefonica/AgentHound). AgenticMart lists it from public repository data.

Is AgentHound safe to use?

AgenticMart scanned AgentHound on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.

What license does AgentHound use?

It is published under the AGPL-3.0 license.

AgentHound alternatives

View more →

Similar ai agents in Research & Analysis, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.

NameStarsLicenceLast updatedScan
AgentHound (this page)
Telefonica
17AGPL-3.0Jul 22, 2026Scanned, no flagged issues
Hermes Agent
NousResearch
259kMITNov 1, 2026Scanned, no flagged issues
Anything LLM
Mintplex-Labs
68kMITOct 30, 2026Scanned, no flagged issues
Khazix Skills
KKKKhazix
22kMITOct 1, 2026Scanned, no flagged issues
Hermes Webui
nesquena
19kMITNov 1, 2026Scanned, no flagged issues
DocsGPT
arc53
18kMITNov 1, 2026Scanned, no flagged issues