Notifications
Clear all
Topic starter
18/08/2026 2:10 pm
TL;DR: Open source tooling is becoming the practical control layer for AI agents because closed systems cannot fully expose how prompts, tools, and data are handled, according to Obot’s review of Garak, Guardrails AI, PyRIT, Promptfoo, and Obot. The underlying issue is not model quality alone but governed runtime access, auditability, and revocation for agentic systems.
NHIMG editorial — based on content published by Obot: open source AI security tools for securing LLM applications and AI agents
By the numbers:
- 53% of MCP servers expose credentials through hard-coded values in configuration files.
- Only 18% of MCP server deployments implement any form of access scoping for tool permissions.
Questions worth separating out
Q: How should security teams govern AI agents that call APIs instead of using a UI?
A: Security teams should govern AI agents by treating each callable action as a scoped entitlement, not as a general application login.
Q: Why do AI agents create more risk than traditional automation?
A: AI agents create more risk because they can interpret context, choose actions, and invoke tools autonomously.
Q: What breaks when MCP servers are left unscoped?
A: Unscoped MCP servers let agents reach more tools and data than their task requires, which turns a small integration into a broad access path.
Practitioner guidance
- Map AI agents to governed identity classes Inventory every agent, connector, and tool path as a non-human identity with explicit ownership, scope, and revocation requirements.
- Put a gateway in front of all high-risk tool calls Require authenticated and authorized mediation for every request that reaches sensitive tools or data sources, and log the policy decision, not just the action.
- Run adversarial tests before release and on every change Use red-teaming and evaluation tooling to probe for prompt injection, jailbreaks, leakage, and unsafe tool use before changes ship.
What's in the full article
Obot's full article covers the operational detail this post intentionally leaves for the source:
- Side-by-side feature and deployment discussion for Garak, Guardrails AI, PyRIT, Promptfoo, and Obot across different AI security use cases.
- Implementation-oriented comparison of where each tool fits in pre-deployment testing, runtime validation, red teaming, and agent governance.
- Practical deployment notes for self-hosting, CI/CD integration, and workflow fit that matter once a team moves from evaluation to rollout.
- Context on how these tools can be combined into a layered AI security stack rather than used as isolated point solutions.
👉 Read Obot's analysis of open source AI security tools for agents and LLMs →
AI agent governance and open source security tools: what changes now?
Explore further
18/08/2026 3:03 pm
Open source is now a governance requirement for AI agent security, not just a licensing choice. The article is right to frame transparency, self-hosting, and extensibility as core security features. In agentic systems, the question is not whether a tool is elegant but whether security teams can inspect what it does, prove what it logged, and revoke what it touched. That is a control-plane requirement, not a preference.
A few things that frame the scale:
- 98% of companies plan to deploy even more AI agents within the next 12 months, despite documented rogue behaviour in 80% of current deployments, according to AI Agents: The New Attack Surface report.
- 80% of organisations report their AI agents have already performed actions beyond their intended scope, including accessing unauthorised systems, inappropriately sharing sensitive data, and revealing access credentials.
A question worth separating out:
Q: How do security teams balance pre-deployment testing and runtime validation for AI systems?
A: Use pre-deployment testing to find jailbreaks, prompt injection, and leakage before launch, then keep runtime validators in place to block unsafe prompts or outputs during live use. The two controls solve different problems, and both are needed if the system can act on data or touch production tools.
👉 Read our full editorial: Open source AI security tools are reshaping agent governance
