agentic_security
★ 2.0k
vs
norviq
★ 26
agentic_security vs norviq
agentic_security: Agentic Security is an open-source vulnerability scanner designed to protect AI systems and LLM agent workflows. It detects and mitigates threats like jailbreaks, fuzzing, and multimodal attacks.; norviq: Norviq is a policy enforcement point that intercepts and evaluates every LLM agent tool call against OPA/Rego policies on Kubernetes. It prevents potential risks like prompt injection or reasoning errors by ensuring tools only run if explicitly allowed by policy, enhancing AI safety and auditability.
01
TL;DR
agentic_securitySecurity & Safety · ★ 2.0k
When to choose:
- You want to red-team your own LLM or agent endpoint with multimodal attacks, multi-step jailbreaks, fuzzing and RL-based probes.
- Your target is any HTTP API: you describe it with a plain-text request spec.
- You want a CI check with a budget and a failure threshold, and your own CSV prompt datasets.
When to skip:
- You are not authorised to test the target: only scan systems you own or may test.
- You need to vet MCP servers before installing them: it tests model endpoints, not MCP server code.
- API cost is a problem: scans send many attack prompts.
norviqSecurity & Safety · ★ 26
Preventing LLM agents from executing unauthorized or dangerous tool calls, such as `execute_sql` or `send_email` without explicit policy approval.
02
Side-by-Side Comparison
Field
agentic_securitynorviqCategory
Security & Safety
Security & Safety
Stars
★ 2.0k
★ 26
License
Apache-2.0
Apache-2.0
Install Command
pip install agentic_security
kubectl create namespace norviq && kubectl create namespace default && helm install norviq oci://ghcr.io/norviq-dev/charts/norviq --version 0.2.5 -n norviq --set 'policyQuotaNamespaces={default}' --set config.dbSslMode=disable
Updated
4d ago
3w ago
Open Source
Yes
Yes
Tags
AI Security, LLM, Vulnerability Scanner
LLM Agents, Policy Enforcement, Kubernetes
03
Features
agentic_security01Multimodal Attacks
02Multi-Step Jailbreaks
03Comprehensive Fuzzing
04API Integration & Stress Testing
05RL-Based Attacks
norviq01Policy enforcement using OPA/Rego for sub-second, fail-closed evaluation of agent tool calls.
02Kubernetes-native deployment with custom resource definitions (CRDs), a mutating webhook, and Helm chart support.
03Supports workload identity using SPIFFE/SPIRE SVIDs for granular, per-agent-class and per-namespace policy scoping.
04Provides a Console UI for policy catalog/editor, attack/asset graphs, agent trust management, and audit stream.
05Includes a red-team suite with built-in adversarial tests to validate policy effectiveness against attacks like prompt injection or SQLi.
04
Use Cases
agentic_security↳AI system vulnerability testing
↳LLM security research
↳DevSecOps for AI
norviq↳Preventing LLM agents from executing unauthorized or dangerous tool calls, such as `execute_sql` or `send_email` without explicit policy approval.
↳Ensuring compliance by enforcing policy-driven gates on agent tool interactions and providing comprehensive audit logs for all decisions.
↳Implementing fine-grained security policies for different agent classes and namespaces within a Kubernetes environment.
↳Detecting and blocking prompt injection or reasoning errors that could lead to malicious tool execution or data exfiltration.
05
Best For
agentic_securityTrending
norviq—
FAQ
FAQ
What is the difference between agentic_security and norviq?
Both agentic_security and norviq are in the Security & Safety category. agentic_security has 2.0k stars, while norviq has 26 stars.
Which is better, agentic_security or norviq?
The best choice depends on your use case. Choose agentic_security if AI system vulnerability testing, and norviq if Preventing LLM agents from executing unauthorized or dangerous tool calls, such as `execute_sql` or `send_email` without explicit policy approval..
Is agentic_security free or open source?
Yes, agentic_security is open source on GitHub (Apache-2.0).
Is norviq free or open source?
Yes, norviq is open source on GitHub (Apache-2.0).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→