IDRIS

You can't secure what you can't see. Discover every agent. Trace every permission.
6
Modules
10
Discovery Sources
5
Compliance Frameworks
553
Tests Passing
pip install red-specter-idris
82 non-human identities per human user / 84% can't pass an agent behaviour audit / 60% have no AI governance policy / Shadow AI is already in your environment / Agents with no accountable owner / Over-privileged credentials never rotated / $670K additional breach cost from shadow AI 82 non-human identities per human user / 84% can't pass an agent behaviour audit / 60% have no AI governance policy / Shadow AI is already in your environment / Agents with no accountable owner / Over-privileged credentials never rotated / $670K additional breach cost from shadow AI

The Invisible Threat

You know your human users. You don't know your AI agents. Non-human identities now outnumber human users 82 to 1 in enterprise environments. Shadow agents are deployed, forgotten, over-privileged, and unaccountable. You cannot defend what you cannot enumerate. IDRIS enumerates everything.

Shadow AI Everywhere

Developers deploy Slack bots, automation agents, LLM-powered tools, and MCP server integrations without central visibility. By the time security knows an agent exists, it has already been running for months with production access.

Permission Sprawl Is Invisible

Every agent accumulates permissions over time. Database read. S3 write. GitHub token. OAuth delegation chain. Nobody traces what each agent can actually access. Over-privilege is universal. Escalation paths are unmapped.

No Accountable Owner

Agents outlive the people who built them. The original developer left six months ago. The agent still runs. Nobody owns it. Nobody knows what it does. When it's compromised, nobody receives the alert.

Compliance Audits Fail

EU AI Act, NIST AI RMF, and OWASP Agentic Top 10 require you to inventory and govern AI agents. 84% of organisations doubt they could pass an audit. IDRIS builds the evidence base the audit requires.

Trust Chains Are Hidden

Agent A delegates to Agent B which calls Tool C which has access to Service D. The blast radius of a single compromised credential spans the entire chain. Nobody has mapped it. IDRIS maps it automatically.

Discovery Finds Nothing

Traditional asset management doesn't know what an AI agent looks like. It can't fingerprint LLM API traffic, parse MCP configs, or identify agentic patterns in cloud function deployments. IDRIS does all three.

6 Core Modules

Each module targets a distinct layer of the agent identity and governance problem. Together they produce a complete picture no single tool can deliver.

Module 01

Agent Discovery Engine

Continuously scans cloud, SaaS, and on-premises environments to discover every deployed agent — sanctioned or shadow. 10 discovery sources, LLM endpoint fingerprinting, API call pattern analysis.

Module 02

Permission Mapper

Traces what each agent can access. Databases, APIs, code repos, production systems. Identifies over-privilege, orphaned credentials, and privilege escalation paths across 8 escalation rules.

Module 03

Ownership Tracer

Determines who created each agent, who owns it now, and whether they're still with the organisation. Maps ownership gaps — agents running with no accountable human are flagged critical.

Module 04

Identity Graph

Visualises the full relationship map. Agent-to-agent trust, delegation chains, permission maps, hidden transitive trust chains. Blast radius analysis — if this agent is compromised, what else is at risk.

Module 05

Compliance Audit Generator

Produces compliance-ready reports mapped to EU AI Act, NIST AI RMF, CSA AI Safety Initiative, OWASP Agentic Top 10, and UK AISI. Full gap analysis with remediation recommendations.

Module 06

NEMESIS Integration Feed

The unique capability no competitor can replicate. Feeds discovered agents directly into NEMESIS for adversarial validation. IDRIS finds it, NEMESIS proves it's exploitable. The loop closes.

10 Discovery Sources

IDRIS reaches every corner of your environment. Cloud platforms, SaaS integrations, CI/CD pipelines, container registries, git repositories, and raw network traffic — all scanned for agentic presence.

AWS
Lambda, ECS, Bedrock, SageMaker, Step Functions
Azure
Functions, AKS, Azure OpenAI, Logic Apps, Bot Service
GCP
Cloud Functions, Cloud Run, Vertex AI, GKE
SaaS
Slack bots, Teams apps, Salesforce, ServiceNow, Zapier
API Gateway
Proxy logs, routing rules, LLM API traffic analysis
MCP
MCP server endpoints, configs, registries
CI/CD
GitHub Actions, GitLab CI, Jenkins pipelines
Container
Docker, docker-compose, Kubernetes pods
Network
Port scanning, LLM endpoint fingerprinting
Git
Agent configs, code imports, .env files, system prompts

The Full Lifecycle

IDRIS
Discovers
NEMESIS
Validates
AI SHIELD
Defends

Discovery → Validation → Defence.
Nothing assumed known. Nothing assumed safe. Nothing assumed defended.

5 Compliance Frameworks

Every finding is mapped to the regulatory frameworks your auditors and legal teams will ask about. IDRIS doesn't just find gaps — it builds the audit evidence you need to close them.

EU AI Act
7 requirements assessed
NIST AI RMF
8 requirements assessed
CSA AI Safety
8 requirements assessed
OWASP Agentic Top 10
10 requirements assessed
UK AISI
3 principles assessed
6
Modules
10
Discovery Sources
5
Compliance Frameworks
553
Tests Passing
0
Failures

553 Tests

Test Breakdown by Module

Agent Discovery
120 tests
Permission Mapper
100 tests
Ownership Tracer
80 tests
Identity Graph
80 tests
Compliance Audit
80 tests
NEMESIS Feed
60 tests
CLI + Crypto
90 tests
UNLEASHED
43 tests

The Complete Offensive Pipeline

IDRIS is the discovery and governance layer of NIGHTFALL. It feeds discovered agents directly into NEMESIS for adversarial validation and into AI Shield for runtime defence.

Stage 1
FORGE
LLM Testing
Stage 2
ARSENAL
Agent Testing
Stage 3
PHANTOM
Swarm Assault
Stage 4
POLTERGEIST
Web Siege
Stage 5
GLASS
Traffic Interception
Stage 6
NEMESIS
Adversarial AI
Stage 7
SPECTER SOCIAL
Human Layer
Stage 8
PHANTOM KILL
OS/Kernel
Stage 9
GOLEM
Physical Layer
Stage 10
HYDRA
Supply Chain
Discovery
IDRIS
Governance
Defence
AI Shield
Defence
SIEM
redspecter-siem
SIEM Integration
Pure Engineering
Zero External Tools. Zero Wrappers.

Every discovery module, every graph algorithm, every compliance checker — written from scratch in pure Python. No subprocess calls. No third-party scanners wrapped in a UI. Actual engineering from the ground up.

6
Core Modules
10
Discovery Sources
0
Subprocess Calls
0
External Dependencies

Security Distros & Package Managers

Kali Linux
.deb package
Parrot OS
.deb package
BlackArch
PKGBUILD
REMnux
.deb package
Tsurugi
.deb package
PyPI
pip install
macOS
pip install
Windows
pip install
Docker
docker pull

Authorised Use Only

Red Specter IDRIS is intended for authorised security testing and governance activities only. Unauthorised scanning of environments you do not own or have explicit permission to assess may violate the Computer Misuse Act 1990 (UK), Computer Fraud and Abuse Act (US), and equivalent legislation in other jurisdictions. Always obtain written authorisation before conducting any security assessments. Apache License 2.0.

Ed25519 Cryptographic Override
IDRIS UNLEASHED

Standard mode discovers, maps, audits, and reports. Passive. Safe to run in any environment.

UNLEASHED mode turns discovery into destruction. Every agent IDRIS finds is fed through the full Red Specter offensive stack for live adversarial validation. Ed25519 gated. Founder's machine only. RESTRICTED classification. Air-gapped output. Never transmitted.