Search Results for "ard attack tool"

ADR, short for Agentic AI Detection and Response, is an enterprise security system for monitoring and evaluating AI agents. It captures agent intent, tool activity, and execution traces from coding assistants, internal automations, and customer-facing agents. A normalized sensor layer provides observability across multiple agent tools and operating systems. ADR-Bench supplies more than 300 realistic tasks, 133 MCP servers, and coverage of 17 documented agent attack techniques. Its two-tier detector combines high-recall triage with deeper agentic analysis of suspicious sessions. ...

...Claw-Hunter addresses this emerging threat landscape by providing visibility into these agents, helping organizations identify instances running within their environments. It focuses on uncovering “shadow AI,” which refers to unauthorized or unmanaged AI agents that operate outside traditional security controls. The tool performs risk assessment by auditing agent permissions, capabilities, and access levels, allowing security teams to evaluate potential attack surfaces. It also helps ensure that these agents do not unintentionally expose sensitive data or create unauthorized access paths across systems.

...Users can deploy it via Docker or scripts to get a modern web UI that guides them through tasks like scanning third-party frameworks for known CVEs and experimenting with prompt security against attack vectors. The tool provides both a visual interface and a comprehensive API, making integration with internal security systems or CI/CD pipelines practical for ongoing risk management.

Superagent is an open-source AI safety platform built to protect applications from prompt injections, data leaks, and harmful outputs. It embeds real-time safety directly into AI workflows, helping teams secure models before threats cause damage. Superagent provides guardrails that block jailbreaks, prompt manipulation, and sensitive data exfiltration. It includes redaction tools to remove PII, PHI, and secrets automatically from text. The platform also scans code repositories to detect...

Agent of Death is an AI powered vulnerability scanner for AI agents. The attack surface for AI agents is real and well-documented — prompt injection, jailbreaks, data exfiltration via tool calls, adversarial inputs, system prompt leakage, insecure tool permissions, lack of output sanitization, etc. Probe library — 41 probes across 8 categories Prompt Injection (8), Jailbreak (7), System Prompt Exfiltration (5), Data Leakage (5), Tool Abuse (6), Indirect Injection (4), Token Smuggling (3), Agentic Behaviour (3)