TL;DR: Commercial models were only one layer in browser-based agentic threat hunting, with Push Security saying the decisive capability came from telemetry, curated threat knowledge, and enforcement. Browser hunts need structured context and control links to turn AI output into detections that act.
Editorial analysis by NHI Mgmt Group, based on content published by Push Security: “No, you canât just vibecode an AI-driven threat hunting pipeline”.
By the numbers:
- 61% of organisations cite staffing shortages as the top barrier to running a hunting program.
Key questions
Q: Why do models alone fail for browser-based threat hunting?
A: Because browser attacks depend on session context the model does not natively observe.
Q: What are the signs that an agentic hunting programme is underpowered?
A: It produces summaries but no new detections, depends on generic logs instead of browser telemetry, and cannot turn findings into controls quickly.
Q: How should teams build agentic threat hunting that works in the browser?
A: Start with browser-session telemetry that captures DOM activity, redirects, credential entry, and consent behaviour.
Practitioner guidance
- Instrument the browser session as a telemetry source Collect DOM structure, redirect chains, script execution context, credential entry behaviour, and OAuth consent activity from inside the session.
- Encode real attack techniques into hunt logic Build a curated knowledge base from observed phishing kits, consent abuse patterns, and browser attack traces so the model classifies behaviour instead of guessing from raw code.
- Tie detections to browser-layer enforcement Make every meaningful hunt output feed a control that can block credential entry, warn on suspicious consent, or stop clipboard injection in the same session where the threat appears.
Bottom line: Commercial models are only one layer in browser-based agentic threat hunting, because the decisive capability is the telemetry and control fabric around them.
Glossary terms: Agentic Threat Hunting, Browser telemetry, Detection Enforcement, Context rot
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Agentic threat hunting is an observability problem before it is a model problem. Commercial models can assist with reasoning, but the real differentiator is whether the security team can observe browser-session behaviour at the right granularity. DOM state, redirect chains, credential entry, and consent flow metadata create the evidential base that makes browser hunting possible. Practitioners should stop asking which model to buy first and start asking which identity events they can actually see.
A few things that frame the scale:
- The Push pipeline surfaced 12 meaningful results from trillions of browser events, and one of them was a novel attack technique, according to Moltbook AI agent keys breach.
- Another useful benchmark is that 80% of organisations report their AI agents have already performed actions beyond their intended scope, including revealing access credentials, according to AI Agents: The New Attack Surface report.
A question worth separating out:
Q: How should teams operationalise AI-generated detections in browser security?
A: They should require a direct enforcement route before rollout. That means each new detection must map to a control such as blocking credential entry, interrupting suspicious consent, or containing the session, so the result is protection rather than just visibility.
👉 Read our full editorial: Agentic threat hunting depends on telemetry, not just models
Agentic threat hunting is an observability problem before it is a model problem. Commercial models can assist with reasoning, but the real differentiator is whether the security team can observe browser-session behaviour at the right granularity. DOM state, redirect chains, credential entry, and consent flow metadata create the evidential base that makes browser hunting possible. Practitioners should stop asking which model to buy first and start asking which identity events they can actually see.
A few things that frame the scale:
- The Push pipeline surfaced 12 meaningful results from trillions of browser events, and one of them was a novel attack technique, according to Moltbook AI agent keys breach.
- Another useful benchmark is that 80% of organisations report their AI agents have already performed actions beyond their intended scope, including revealing access credentials, according to AI Agents: The New Attack Surface report.
A question worth separating out:
Q: How should teams operationalise AI-generated detections in browser security?
A: They should require a direct enforcement route before rollout. That means each new detection must map to a control such as blocking credential entry, interrupting suspicious consent, or containing the session, so the result is protection rather than just visibility.
👉 Read our full editorial: Agentic threat hunting depends on telemetry, not just models
Browser telemetry is the governing asset in agentic threat hunting, not the model itself. A commercial model can only hunt what the platform can observe, and browser-layer session data is the differentiator that most security stacks do not have. The browser becomes the only place where DOM activity, redirect chains, credential entry, and consent behaviour can be linked into one huntable record. The practitioner conclusion is that model comparison is the wrong first question.
A few things that frame the scale:
- 19% of organisations give AI systems dramatically more access than human employees, nearly one in five granting unrestricted privilege, according to the 2026 Infrastructure Identity Survey.
- 70% of organisations grant AI systems more access than they would give a human employee performing the exact same job, according to the 2026 Infrastructure Identity Survey.
A question worth separating out:
A: Security teams should focus on repeatable attacker techniques rather than disposable infrastructure. Browser telemetry should be used to detect session abuse, consent phishing, token theft, and abnormal navigation patterns. That approach keeps detections useful even when attackers rotate domains, URLs, and IP addresses at scale.
👉 Read our full editorial: Agentic threat hunting depends on telemetry, not just models