Know the Threat. Own the Defense.
Xtrinel builds VAAST, the vulnerability scanner for LLM-integrated applications. Find prompt injection, tool-call abuse, RAG poisoning, and agentic pipeline flaws before they reach production.
Supported by
The AI Attack Surface
Traditional DAST misses most of it.
LLM-integrated applications introduce a class of vulnerabilities that conventional scanners were never built to reach. VAAST covers the gap.
Prompt Injection
Adversarial inputs that hijack instructions, exfiltrate system prompts, or coerce the model into forbidden actions. VAAST catalogs direct, indirect, and multi-turn variants.
Tool-Call Abuse
Agentic stacks expose tool surfaces as first-class APIs. VAAST's MCP Scanner enumerates callable tools and probes each one for parameter injection, privilege escalation, schema confusion, and unauthorized state changes.
RAG Poisoning
Retrieval layers trust their corpus. VAAST inspects ingestion paths, checks for prompt-level poisoning, and flags documents that coerce downstream reasoning.
Agentic Pipeline Abuse
Chained agents, plan-and-execute loops, and autonomous workflows create new blast radii. VAAST maps the full graph and identifies failure modes unique to long-horizon runs.
VAAST in Action
From scan to findings.
Point VAAST at your LLM endpoint, run the payload catalog, and review and export what it finds.
Run VAAST's payload catalog against your LLM app.
Xtrinel
Built for the agentic AI era.
How VAAST is different
Detections you can read, verify, and challenge.
No black boxes. Every finding comes with evidence, every detection is documented, and VAAST only runs where you're authorized to test.
Research-Led
Detections are documented in public writeups from HYDRACUDA, our research division.
Authorized Only
VAAST is built for practitioners with written authorization. Our license agreement requires you to say so before every engagement.
Exportable Evidence
Every finding includes the exact payload and the model’s response, exportable as JSON or HTML.
Bring VAAST into MCP-compatible AI agents and clients. Read-only access to your local scan findings and workspaces.
npx -y @xtrinel/vaast-mcpReady to map your AI attack surface?
Start with the free tier. Upgrade when your findings pile up.