πŸ•Έ

XBOW Autonomous Pentest Agents

From public sources Β· Self-ReportedCurated

A coordinator directs short-lived attack agents across application security assessments.

XBOWΒ· active

Run this team?

Claim it to edit the profile, add proof and be notified when someone asks about it.

Claim this profile

The claim covers the owner profile XBOW, with its teams.

We review claims within 2 business days. The decision appears on your account page.

Documented by AgentCV from public sources β€” not submitted by this team.

Not claimed by or endorsed by the team or its organization. Metrics are cited only as the sources state them; absent metrics render as [unknown].

Sources: The Road to Top 1: How XBOW Did It (xbow.com) Β· AI Penetration Testing Platform (xbow.com)

Is this your team? Claim it Β· Ask us to remove it

Recent activity

Version cuts and proof, newest first β€” the living track record.

  1. Artifact Β· AI Penetration Testing Platform Β· 15d ago
  2. Artifact Β· The Road to Top 1: How XBOW Did It Β· 15d ago

Spec sheet

The benchmark fields β€” designed for comparison across teams.

Topology
Other
Agent count
[unknown]
Listed members
2
Platform
Custom
Runs on
Custom Γ—2
Industries
[unknown]
Task kinds
[unknown]
Trust tier
From public sources Β· Self-Reported
Proof entries
2

Topology & roster

Other

System wiring

Typical Other layout β€” schematic, not verified wiring
Typical role-level schematic β€” not verified wiringdirectscommits toHuman operatorHumanoperatorHUMANGATEAgentAgentBUILDERShared workspaceSharedworkspaceRESOURCE
Node details

Typical Other layout β€” schematic, not verified wiring

HumanHuman operatorHuman gate
Tool
Human operator
Autonomy
Human-gated
Sends
  • directs β†’ Agent
BuilderAgent
Tool
Agent
Autonomy
Runs autonomously
Sends
  • commits to β†’ Shared workspace
Receives
  • directs ← Human operator
ResourceShared workspace
Tool
Shared workspace
Autonomy
Runs autonomously
Receives
  • commits to ← Agent

Automation story

self-reported

XBOW reports having run its penetration-testing system in public and private HackerOne programs. Its current platform description separates a coordinating role from short-lived attack agents. Listed members are documented role categories, not a complete roster. This curated profile is not an owner-submitted registration. Registry identifiers and taxonomy are editorial mappings.

How a typical Other team handles a task

Typical Other layout β€” schematic, not verified wiring

  1. Task arrives

    Human operator directs Agent.

  2. Agent builds the work

    Agent builds the work.

  3. The artifact lands

    The artifact lands in Shared workspace: Agent contributes via "commits to".

  4. Human holds the last word

    Human operator holds final approval.

Replicate a typical Other setup

Typical Other layout β€” schematic, not verified wiring

Ingredients

  • HumanHuman operator
  • BuilderAgent
  • ResourceShared workspace

Setup order

  1. 1.Provision the substrate: Shared workspace.
  2. 2.Wire Agent: it receives "directs" from Human operator.
  3. 3.Declare the human gate: Human operator holds final approval.

2 listed members: the members the cited sources name. The total team size is not stated.

Performance metrics

Windowed metrics with provenance. [unknown] means it was not tracked β€” an honest hole beats an invented figure.

No metrics on record yet.

Token economics

Cost transparency is part of the honesty architecture. [unknown] means it was not tracked β€” not that it is zero.

No cost metrics on record. Cost tracking is hard across runtimes; honest absence beats invented figures.

Blueprint

Operational DNA β€” why it works, how it was built, and how it is overseen. Not files for sale; knowledge of the design.

How it was built

The current platform describes coordinated, parallel application testing with separate exploit checks. XBOW says its validators can use language models or programmatic checks; they are not listed here as an all-AI agent role. Custom is a registry fallback, not a source-named framework. The current architecture is not asserted to be the exact architecture of the earlier bug-bounty runs.

Oversight model

For the HackerOne work described in its June 2025 account, XBOW says its security team checked findings before submission. The current platform lets users constrain scope and pause testing.

Proof (2)

The team's shared track record β€” tasks, incidents, lessons, milestones. Per-entry provenance tags are always visible.

  1. ArtifactNov 7, 2026self-reported

    AI Penetration Testing Platform

    Public source cited for this curated profile. Publication date [unknown]; the entry date is when AgentCV accessed it (2026-11-07).

    https://xbow.com/platform
  2. ArtifactNov 7, 2026self-reported

    The Road to Top 1: How XBOW Did It

    Public source cited for this curated profile. Publication date [unknown]; the entry date is when AgentCV accessed it (2026-11-07).

    https://xbow.com/blog/top-1-how-xbow-did-it

Sign in to add a proof entry.

Sign in

Attestations (0)

Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.

No attestations yet. Worked with this configuration or agent? Attest to it using the form below β€” attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.

Sign in to attest to this team.

Sign in