Read the free interactive preview of AI Security From PsyOps to CyberOps Start Reading Free →
LIVE DATA + CURATED FRAMEWORKS

Threat Intelligence

Recent vulnerability activity pulled directly from NVD and CISA at page load, alongside the frameworks we ground our own testing and controls in: OWASP's LLM and Agentic Top 10s, MITRE ATLAS, NIST's AI Risk Management Framework, and ISO/IEC 42001.

Connecting to sources…

The two panels below call NVD and CISA directly from your browser — nothing passes through our servers. If your network blocks either host, that panel falls back to a direct link instead of stale data.

Recent CVEs — AI & LLM keyword match

Source: NIST National Vulnerability Database (NVD API 2.0), live
Loading
Querying services.nvd.nist.gov…

Recently added — CISA Known Exploited Vulnerabilities

Source: CISA KEV Catalog, live · all sectors, not AI-specific
Loading
Querying cisa.gov…

OWASP Top 10 for LLM Applications — 2025

genai.owasp.org →
LLM01
Prompt Injection

Crafted input overrides system instructions, directly or via hidden content the model processes.

LLM02
Sensitive Info Disclosure

Training data, secrets, or context bleed into outputs, logs, or traces.

LLM03
Supply Chain

Compromised models, datasets, libraries, or hosting providers in the pipeline.

LLM04
Data & Model Poisoning

Malicious training, fine-tuning, or retrieval data shapes model behavior.

LLM05
Improper Output Handling

Downstream systems trust model output without validation or sanitization.

LLM06
Excessive Agency

Excessive functionality, permissions, or autonomy granted to a model or agent.

LLM07
System Prompt Leakage

Instructions, keys, or internal logic embedded in the system prompt get exposed.

LLM08
Vector & Embedding Weaknesses

Poisoned, unauthorized, or manipulated access to RAG vector stores.

LLM09
Misinformation

Confident, plausible, and false output — hallucination treated as fact.

LLM10
Unbounded Consumption

Resource-heavy prompts or loops drive cost, denial-of-service, or model theft.

OWASP Top 10 for Agentic Applications — 2026

genai.owasp.org →
ASI01
Agent Goal Hijack

Malicious content alters an agent's objective or reasoning path mid-task.

ASI02
Tool Misuse & Exploitation

Legitimate tools get bent into destructive or unintended actions.

ASI03
Identity & Privilege Abuse

Agents operate with broader permissions than their task requires.

ASI04
Agentic Supply Chain Compromise

Compromised skills, plugins, or agent-to-agent dependencies.

ASI05
Unexpected Code Execution

Agent-generated or agent-triggered code runs beyond its intended sandbox.

ASI06
Memory & Context Poisoning

Poisoned long-term memory or embeddings reshape future decisions.

ASI07
Insecure Inter-Agent Comms

Spoofed or tampered messages between agents in a multi-agent system.

ASI08
Cascading Failures

Small errors propagate and amplify across chained agents and workflows.

ASI09
Human-Agent Trust Exploitation

Confident agent output leads a human to approve a harmful action.

ASI10
Rogue Agents

A compromised or misaligned agent acts harmfully while appearing legitimate.

Frameworks we ground our methodology in

ADVERSARY TTPS

MITRE ATLAS

A living matrix of real-world adversary tactics and techniques against AI/ML systems — reconnaissance, ML model access, staging, exfiltration, and impact — built on the same structure as ATT&CK, with case studies of actual incidents.

atlas.mitre.org →
GOVERNANCE

NIST AI Risk Management Framework

Four core functions — Govern, Map, Measure, Manage — for identifying and reducing AI risk across an organization. We use it as the shared vocabulary for translating red-team findings into governance action.

nist.gov →
MANAGEMENT SYSTEM

ISO/IEC 42001

The first international standard for an AI management system — governance, risk, and lifecycle controls for organizations that build or deploy AI. Referenced as a target for clients pursuing formal certification.

iso.org →

On sourcing: the two panels above call the NVD and CISA APIs directly from your browser at page load — we don't proxy, cache, or store what they return. The CVE search is keyword-matched against NVD for "large language model" and "artificial intelligence," which surfaces relevant results but isn't a guarantee of completeness — always cross-check against the source for anything decision-critical. The CISA KEV catalog isn't AI-specific; it's shown because it's one of the highest-signal "what's actively being exploited right now" feeds available publicly. The OWASP, MITRE, NIST, and ISO summaries above are maintained by us and refreshed periodically against the source publications; they are not live API calls, since none of those bodies publish one for this content — click through to each source for the authoritative, current version.