armariusOne click, always on. Zero extra API calls. Neutralizes prompt injection the moment it arrives. Never interrupts your work. No setup, no code required.
Install via ClawdBot CLI:
clawdbot install tatlantis/armariusGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/tatlantis/armariusAudited Apr 17, 2026 · audit v1.0
Generated Mar 22, 2026
Protects AI-powered customer support agents from malicious instructions hidden in user-uploaded documents or external API responses, ensuring agents only follow authorized workflows. Prevents attackers from injecting commands via support tickets or attachments to manipulate agent behavior.
Safeguards AI financial analysts processing external market reports, emails, or regulatory filings from prompt injections that could alter investment advice or transaction instructions. Neutralizes attempts to override user-defined risk parameters or compliance rules embedded in content.
Secures AI assistants handling patient records, lab results, or medical literature from injected directives that might compromise data privacy or clinical guidelines. Ensures external content is treated as data only, preventing unauthorized actions like sharing sensitive information.
Protects AI tools analyzing contracts, case files, or legal databases from prompt injections that could modify interpretation or output. Prevents external content from overriding user instructions on confidentiality or legal standards, maintaining integrity in document processing.
Secures AI systems managing product listings, reviews, or supplier data from malicious injections in external feeds or APIs. Neutralizes attempts to alter pricing, inventory updates, or customer communications without user authorization.
Offers Armarius as a cloud-based service with tiered pricing based on usage volume or number of protected agents, providing regular updates and support. Revenue streams include monthly/annual subscriptions and enterprise licensing for large-scale deployments.
Sells perpetual or annual licenses to large organizations for on-premises or private cloud integration, with customization options and dedicated support. Revenue is generated through upfront license sales and ongoing maintenance contracts.
Provides a free basic version for individual developers or small teams, with paid upgrades for advanced features like detailed analytics, multi-agent support, or priority response. Revenue comes from premium subscriptions and add-on services.
💬 Integration Tip
Integrate Armarius early in your AI pipeline to classify channels and enforce rules automatically, requiring no code changes for basic protection. Test with sample injection attempts to ensure logging works as expected before deployment.
Scored Jun 19, 2026
Manage and operate ClawSec Monitor v3.0, a MITM HTTP/HTTPS proxy that logs AI agent traffic, detects exfiltration and injection threats in real time.
Scan Clawdbot and MCP skills for malware, spyware, crypto-miners, and malicious code patterns before you install them. Security audit tool that detects data exfiltration, system modification attempts, backdoors, and obfuscation techniques.
Security scanner for ClawHub skills. Vet third-party skills before installation — detect dangerous patterns, suspicious code, and risky dependencies.
Security audit and hardening for AI agents — credential hygiene, secret scanning, prompt injection defense, data leakage prevention, and privacy zones.
Scan OpenBot/Clawdbot skills for security vulnerabilities, malicious code, and suspicious patterns before installing them. Use when a user wants to audit a skill, check if a ClawHub skill is safe, scan for credential exfiltration, detect prompt injection, or review skill security. Triggers on security audit, skill safety check, malware scan, or trust verification.
OpenClaw skill discovery, security vetting & install. Searches 3000+ curated skills from ClawHub registry and awesome-openclaw-skills catalog. Scores credibility, detects prompt injection & malicious patterns, manages installations. Quick-checks GitHub for new skills.