Research Dashboard

live

Aggregate across the OpenA2A honeypot network.Last updated: 8/23/2026, 15:54:33 UTC

All metrics are measured events from deployed honeypots. No seeded, demo, or synthetic values are shown on this page.

Total Interactions
631,460
Every request to any honeypot page — visits, file fetches, canary hits
Unique Fingerprints
97,267
Distinct client fingerprints seen across all interactions
Payload Callbacks
14,014
A client fetched the canary URL in an injected payload. Attribution shows most are browsers and crawlers, not agents obeying the instruction.
Canary Triggers
64
A client executed a secondary beacon beyond the initial canary fetch — a deeper-engagement signal, rarely fires
Payload Callback Rate
2.2%(14,014 / 631,460)
2.2% of interactions produced a payload callback (a client fetched the URL)
Canary Trigger Rate
0.0%(64 / 631,460)
0.0% of interactions triggered a secondary canary beacon

Drilldowns

Each card opens a full report. Every number traces back to a Registry endpoint — nothing modeled, nothing projected.

Attack Categories

View full →
17 ranked
14,014 total callbacks

Live ranking by the payload category planted on the page that drew the interaction. It ranks our own bait, not any property of the visitor. Top three today:

  • #1prompt-injection4,808
  • #2data-exfiltration2,278
  • #3jailbreak2,152

Daily Network Activity

View full →
631,460
interactions to date

Daily callback trend across every sector plus new attack-surface discovery from HoneyMap. Real growth, real attribution.

Sector Analysis

View full →
7 verticals
healthcare → education

Cross-vertical risk comparison. Sector attribution derived server-side from the Referer of every callback — an agent that fell on the medical trap registers under healthcare, not on agentpwn.com itself.

HoneyMap Surfaces

View full →
23 sources
surfaces + signatures

Independent surface crawl across the public web. Where injection payloads actually hide (script literals, hidden text, HTML comments, alt/aria, meta tags).

Honeypot Verticals

One card per honeypot’s self-declared vertical. The security vertical reflects agentpwn.com itself — its high rate is a selection effect from deliberate testing, not wild capture.

Wild VEIL sites have been live for ~1 month but receive almost entirely commodity-scanner background traffic (WordPress / PHP exploit probes). No AI-agent activity has been observed on any wild site yet. Cards below show whether each vertical has recorded any callback — raw request totals are not displayed because they are dominated by bot noise. Nothing in this population is attributed to an autonomous agent: of the callbacks recorded so far, roughly a third resolve to browsers and link prefetchers, and two thirds predate attribution and were never classified at all.

agentpwn.com

testbed
23.1%
callback share

2,907 of 12,598 scored interactions on this trap produced a callback. A callback is a fetch of the canary URL carried in a payload, not evidence that an agent acted on it.

2,847 callbacks60 canary triggers

How This Data Is Collected

When AI agents browse agentpwn.com, each page contains hidden injection payloads. If an agent follows the injection, it is instructed to call back to our API with the attack details. This data feeds into the OpenA2A threat intelligence ecosystem.

Privacy: IP addresses are hashed before storage. No PII is collected. User-Agent strings are the primary identifier.

Feedback loop: Interactions feed into new HMA scanner checks, DVAA lab scenarios, and threat matrix evidence. The ecosystem gets smarter with every visit.