Skip to main content
Mallory
← Back to News
internet-exposed-serviceai-platform-security

GitGuardian Finds Exposed AI Hacking Frameworks, Including 39 Unauthenticated Agent Zero Services

Attack Surface Exposure · 3 sources · Updated 6d ago · First seen Nov 11, 2026

GitGuardian Finds Exposed AI Hacking Frameworks, Including 39 Unauthenticated Agent Zero Services

GitGuardian identified internet-accessible deployments of AI-powered hacking and penetration-testing frameworks, including management consoles exposed without authentication. A November 7 Shodan snapshot recorded 1,428 services matching ARTEX-family fingerprints, 419 matching PentAGI, and 173 matching Agent Zero. Of the Agent Zero services, 39 were accessible without authentication. The investigation, published November 9, documented insecure deployments rather than a new malware family.

These dual-use platforms connect language models to security tools, enabling legitimate testing but also potentially automating reconnaissance, exploitation, and credential theft. Unauthenticated management interfaces create a risk of unauthorized access to those capabilities. GitGuardian published discovery fingerprints rather than a target list and cautioned that matches require validation: they do not establish compromise or criminal activity. Security teams should verify suspected deployments, remove unnecessary public exposure, and enforce authentication on management consoles.

Is this exposed in your estate?Map this exposure pattern across your cloud, code, and identities.
Map your surface
Event timeline

How this story unfolded

Events from the most recent confirmed update back to the earliest known activity.

5 events · Oct 2026 – Nov 9, 2026
  1. Reported Nov 11, 20266d ago

    Attackers use ARTEX to steal secrets and access cloud resources

    Earlier reporting documented attackers using ARTEX to steal exposed application secrets and access cloud resources, including Azure Key Vault.

    AI Hacking Frameworks Like ARTEX, PentAGI, and Agent Zero Found Running on Internet-Accessible Servers
  2. Nov 9, 20269d ago

    GitGuardian publishes investigation and discovery fingerprints for AI frameworks

    GitGuardian published its technical investigation after examining roughly 45 open-source projects and assessing 41 for internet-facing discovery fingerprints. It released detection descriptions rather than a target list, emphasizing that the findings concerned insecure dual-use deployments and required validation rather than demonstrating a new malware family or confirmed compromise.

    AI Hacking Frameworks Like ARTEX, PentAGI, and Agent Zero Found Running on Internet-Accessible Servers
  3. Nov 7, 202611d ago

    Shodan snapshot identifies AI framework services, including 39 unauthenticated agents

    A November 7 snapshot recorded 1,428 services matching the ARTEX family, 419 matching PentAGI, and 173 matching Agent Zero. Of the Agent Zero matches, 134 displayed a login page and 39 were accessible without authentication; fingerprint matches alone did not establish compromise or criminal activity.

    AI Hacking Frameworks Like ARTEX, PentAGI, and Agent Zero Found Running on Internet-Accessible Servers
  4. Oct 8, 20261mo ago

    ARTEX creator removes original project following abuse reports

    ARTEX's creator removed the original project on October 8, 2026, following reports of abuse, according to GitGuardian.

    AI Hacking Frameworks Like ARTEX, PentAGI, and Agent Zero Found Running on Internet-Accessible Servers
  5. Oct 2026

    102 ARTEX forks and similarly named repositories appear

    GitGuardian reported that 102 ARTEX forks and similarly named repositories appeared during the week of the original project's October 2026 removal.

    AI Hacking Frameworks Like ARTEX, PentAGI, and Agent Zero Found Running on Internet-Accessible Servers
Linked entities

Related entities

Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.

Open in app →

Affected products

4 linked
PentagiPentestagentPentestgptStrix
Do you run this?See where this exposure pattern shows up across your cloud, code, supply chain, and non-human identities.
See Where You're Exposed
Mallory platform

See the full picture, correlated to your attack surface.

This page covers what’s public. Mallory adds the parts that aren’t: which of your assets are affected, which threat actors are using it right now, and what to deploy next.

Exposure mappingMap indicators from this story to your assets and identify affected systems in minutes.
Threat actor evidenceEvery observed campaign, victim, and pivot linked to actors named in this story.
Associated malwareMalware, exploits, and IOCs connected to the activity described here.
Detection signaturesYARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Scheduled alertsGet matching new stories delivered to your team as they break, not the next morning.
AI threadsAsk questions about this story and take action on the answers.