Extension 214 registered from an unfamiliar network
- REGISTER 401 ×312 · 41 extensions tried
- REGISTER 200 · ext 214 · unfamiliar network
Proposed Block the source and force re-registration of extension 214.
AICS by RFactorial · AI cybersecurity
AICS watches your voice agents, workflow automations and private cloud from inside your own environment. It explains every finding with evidence and proposes fixes your team approves.
Extension 214 registered from an unfamiliar network
Proposed Block the source and force re-registration of extension 214.
01 · Why now
AI agents answer calls, move data between systems and run on GPU clusters. Each is a new way in: a caller who talks the agent into something, a workflow that quietly sends data to an unknown webhook, a cluster hijacked to mine crypto.
02 · Products
Watches your voice agents and the phone system behind them.
Checks workflows before they publish and inspects data at every exit.
An analyst for your private-cloud control plane.
03 · Voice AI
A security agent for your AVA voice deployments. It reads transcripts, tool activity, service logs and sign-ins, and connects them to what your phone system is doing: SIP sign-ins and registrations, extension abuse, call redirects and toll fraud.
An attacker repeatedly tries different usernames and passwords against the SIP service.
02:11:09 REGISTER 401 ×312The attacker probes extension numbers.
02:12:40 OPTIONS ext 200–260An account registers from a network it has never used.
02:14:02 REGISTER 200 · ext 214AVA Guard connects these events, identifies the affected account and service, and shows whether the evidence points to failed attempts only or a possible compromise.
An administrator receives the incident report with recommended containment and configuration changes.
Approved responses are applied through supported telephony and security integrations. Every action is logged and reversible; emergency calling is preserved.
One finding: ext 214
Proposed Block the source, force re-registration of extension 214 and restrict its international calling. Emergency calling stays open.
Repeated failures, attempts across many accounts, unusual registrations, and access that follows suspicious activity.
Extension enumeration, suspicious use of internal calling features, and unexpected changes to forwarding, routing or admin settings.
Unusual outbound destinations, concurrent-call spikes, and calling that doesn't fit the account's normal use.
Attempts to manipulate the agent's instructions, reach another customer's records, or take unauthorized business actions.
Changes to authentication, network exposure, permissions, dial plans, rate limits and code, reviewed by your engineers before they ship.
Outcome Earlier detection of telephony compromise attempts, faster investigation, and clearer steps to protect calling access and service continuity.
Starts in monitoring mode. Emergency calling is never blocked. Built for clinics, e-commerce and service providers.
04 · Workflows
Workflows come from many hands. Radon Guard checks each one before it is shared, then watches the data it sends while it runs.
A risk score, an approve, review or block decision, and the badge “Security checks passed for this version”. Every update is checked again.
Inspects every exit (model calls, MCP calls, HTTP and API calls) for personal data, credentials, payment data, national IDs and confidential documents.
Your policy decides per data type and destination: block, mask, warn or record. It checks both directions, so instructions hidden in a tool’s response are caught too.
A user submits a document-processing workflow to the marketplace.
It asks for access to internal files but also contains an undeclared external destination.
node 4 POST unknown-host.ioRadon Guard flags the mismatch, names the responsible node, and holds publication for review.
Later, an approved workflow processes a confidential document.
class: confidentialBefore the document goes to an external model or MCP tool, a policy check decides whether that destination is allowed for this data.
The request is allowed, blocked or safely redacted by your policy, with the reason recorded for the operator.
One finding: node 4
Needs review Held for review
Embedded secrets, suspicious behaviour, and permissions that don't fit the workflow's purpose.
Undeclared destinations, insecure configurations, excessive MCP tool permissions, and changed dependencies.
Phishing, credential collection, prompt injection and unintended data transfer.
Publish, review-required or blocked decisions tied to a specific version and dependency snapshot.
Policy checks before model, MCP and API calls leave the workflow, and inspection of what comes back.
Outcome Safer workflow sharing, visible third-party dependencies, and enforceable controls over where your organisation's data can go.
Runs inside your Radon deployment. Fast classifiers handle routine checks; a model reviews the ambiguous ones. Built for enterprises and public institutions.
05 · Infrastructure
A security agent for your private-cloud control plane. It reasons over tenancy, identity, quota and workload events across virtual machines, GPUs, storage and network.
Fixes arrive as policy, quota, blueprint or RBAC changes through your own approval flow. Findings export to your SIEM.
A service account receives an administrative role it did not have.
09:02:17 role: cluster-adminShortly afterwards, a workload's network policy changes.
09:02:55 netpol 0.0.0.0/0A previously private notebook becomes reachable from outside.
09:03:20 notebook :8888Clastiq Guard correlates the identity change, the policy update and the exposure, and shows the affected tenant, resources and sequence.
It recommends restoring the approved permissions and network configuration.
An authorised operator reviews the proposed changes before anything runs. Findings export to your SIEM.
One finding: tenant ml-research
Proposed Restore the approved role binding and network policy.
Unexpected admin grants, unusual service-account activity, and access that doesn't fit assigned roles.
Services exposed without expected authentication or network limits, and drift from approved blueprints.
Policy inconsistencies and cross-project access, separating potential exposure from evidence of real access.
Unusual workload creation, quota changes and consumption. High GPU use alone is not treated as proof of abuse.
What changed, who or what started it, which resources it touches, and which steps are available.
Outcome Faster investigation of security-relevant infrastructure changes, with findings connected to your actual tenants, policies and workloads.
Runs entirely in your environment, with local models on your GPUs when air-gapped. Built for cloud providers, telcos and regulated institutions.
06 · How it works
Reads evidence inside your environment.
A finding with its evidence and reasoning.
A scoped, reversible fix.
A person decides; every action is recorded.
Transcripts, tool responses and logs are evidence. Never instructions.
07 · Deployment
| Where does it run? | Alongside the system it guards: with your AVA deployment, inside your Radon deployment, and inside your Clastiq environment. |
|---|---|
| Which models? | Fast classifiers plus model review; local models on your GPUs for air-gapped sites. |
| What can it change? | Nothing without approval. It starts read-only in monitoring mode; source code access is optional and read-only. |
| How does it fit our SOC? | Findings export to your SIEM; Clastiq Guard adds a Kubernetes connector. |
| How do we start? | One scoped pilot: one SIP/PBX stack (AVA Guard), your Radon deployment (Radon Guard), or Clastiq events plus identity and one connector (Clastiq Guard). |
| Which frameworks? | Findings are named in OWASP’s LLM and Agentic Top 10 terms. Data stays in-country to support your PDPL obligations. |
Your environment
08 · FAQ
No. AVA Guard, Radon Guard and Clastiq Guard run inside your environment, and air-gapped sites use local models.
No. It proposes; your team approves. Every action is logged and can be reversed.
The Guards are built for AVA, Radon and Clastiq. If you run other systems, talk to us about what fits.
Monitoring mode on one scoped system, a daily brief, and a review of findings with our engineers.
Monitoring mode changes nothing. Responses are scoped, approved and reversible; emergency calling is preserved.
Scoped per deployment; we’ll size it with you in the briefing.
A working session with our engineers. We map the AI systems you run, walk through a real finding and agree a monitoring-mode pilot.