A Fide AI research tool

AI agents in cybersecurity, on the record

A sourced chronicle of how AI agents are used to attack, how they are measured and gated, how they are defended, and how they fail. Every claim links to its evidence, carries a status that changes as new work arrives, and feeds a list of open research questions.

Records
342
Sources
517
Findings
57
Key questions
7
Methods
31
Every record since February 2023AttackCapabilityDefensePolicyOpen the chronicle →

342 records from Feb 1, 2023 to Nov 17, 2026: 116 attack, 25 capability, 137 defense, 64 policy. The chronicle lists every record.

Start here · where things stand

Key questions

Answers, evidence, and history →

The lasting questions about the field. Each answer is revised in the open as evidence arrives, and shows how confident we are and how solid its findings are. What the statuses and flags mean.

1Can prompt injection against AI agents be reliably defended?Not reliably. Bounding what untrusted input can trigger helps, but trust boundaries must survive delegation and tool execution.high confidence2 corroborated, 2 reported, 4 qualifiedRevised Nov 1, 2026 · 4 earlier answers7 updates since review2Where are deployed AI agents actually being exploited?Exploitation often reaches deployed agents through connectors, credentials, tools and packages.moderate confidence7 corroboratedRevised Nov 17, 2026 · 8 earlier answers3Do cyber evaluations of AI agents stay contained?Not reliably. Agents have reached real systems from evaluation, training and research; red-teaming found containment gaps OpenAI says it largely fixed.high confidence5 corroborated, 2 reportedRevised Nov 1, 2026 · 7 earlier answers6 updates since review4How far can measured AI cyber capability be trusted?As a lower or conditional bound. Scores move with budget, pipeline and contamination, and benchmark names or labels can hide different setups.moderate confidence4 reported, 1 qualifiedRevised Nov 1, 2026 · 3 earlier answers5 updates since review5Is AI shifting the balance between finding and fixing vulnerabilities?Discovery is ahead. Verification, triage, coordinated disclosure, safe repair and getting fixes to users remain bottlenecks between AI findings and protection.moderate confidence3 corroborated, 1 qualifiedRevised Nov 1, 2026 · 4 earlier answers8 updates since review6Can AI agents defend and oversee systems on their own?Not reliably. Some designs improve benchmark triage, but autonomous defense lacks operational validation and production oversight of agents has documented gaps.moderate confidence2 corroborated, 1 reported, 2 qualifiedRevised Nov 1, 2026 · 4 earlier answers5 updates since review7How are attackers using AI agents in real operations?To run large parts of intrusions under human direction, including espionage, credential theft and extortion; reported autonomy and success vary.moderate confidence5 corroborated, 1 reportedRevised Nov 17, 2026 · 10 earlier answers
Latest edition ·

Week of Nov 16–22, 2026

Read the edition →

Recent landmarks

Chronicle →

Findings that moved

Ledger →

Status changes caused by new evidence. Our own 14 corrections are in the changelog.

Where research is needed

Research openings

All openings →
New to the field

Reading paths

All 7 paths and every topic →
Site updates

Changelog

Full changelog →
  • Nov 17, 20262 key questions added or revised
  • Nov 17, 20266 records revised
  • Nov 17, 2026Finding reconfirmed: Separating an agent’s control flow from untrusted data can give provable protection against specified forms of hijacking under explicit assumptions.
  • Nov 17, 20262 corrections to findings
How to read this

Records summarize their sources in our words and link to them. Marks of significance () are editorial judgments. Findings carry a status that we change when new evidence arrives, and every record shows whether a Fide editor has reviewed it. What every label means · Methodology.