Skip to content
NewA calmer, faster ZeroHour
StoryThreat actorhighExploited in the wild

BlackHatSect0r Crew Strips AI Agent Safety Controls to Automate Credential Theft and Vishing at Scale

1 source · 2 articlesFirst reported Updated ()5 · 1 read
What's new

First merged summary of this story, combining two GBHackers reports (2026-09-17T07:00:10Z) with a later Cyber Security News report (2026-09-17T09:59:30Z). The later report added: the credential vault's growth from 16,415 to 16,834 between August 11 and 18; precise scan figures (2,759,860 domains queued, 726,989 hosts reached); a scan rate of ~1,200 addresses every ten seconds on ports…

Merged summary · glm-5.3 · rewritten as coverage arrivesSummaries by Vani AI

Socradar exposed 4.9 GB of infrastructure from French-speaking crew BlackHatSect0r && DXQRTXX running a safety-disabled Hermes/DeepSeek AI agent that harvested 16,834 credentials, scanned 2,759,860 domains, and prepared vishing against ~450,000 French telecom…

Socradar researchers analyzed an exposed operation server (4.9 GB across 9,299 files) belonging to the French-speaking crew BlackHatSect0r && DXQRTXX. The crew ran a self-hosted Nous Research Hermes agent on a DeepSeek model with refusal instructions/memory removed and safety controls disabled via HERMES_DISABLE_SAFETY=1, using it for scanning, secret hunting, and Telegram reporting. The exposed Go-based DXSCAN C2 platform, served on port 8080, carried 200+ secret-detection patterns (.env, YAML, JSON, PHP, WordPress), a credential vault of 16,834 records (including AWS keys, GitHub tokens, and Stripe keys) that grew from 16,415 between August 11 and 18, and scanning activity that queued 2,759,860 domains, reached 726,989 hosts, generated 1.37 million IP addresses, and probed at roughly 1,200 random addresses every ten seconds across ports 80, 443, and 8080. The server also held roughly 450,000 French telecom subscriber records used to prepare vishing lures impersonating Société Générale, with 1,697 subscribers aged 50+ targeted by calls directing victims to attacker-controlled phone numbers, plus JWT-forging tooling aimed at a cryptocurrency exchange that used the literal signing secret 'secret', phishing tools, and extortion material. 82 of 230 harvested SMTP configurations were verified for reuse as phishing relays. Access came from misconfigurations such as public cloud buckets and exposed .env files rather than new vulnerabilities; the one cited vulnerability, CVE-2026-42530, is an NGINX HTTP/3 QPACK use-after-free fixed in version 1.31.2. Defenders are urged to hunt for HERMES_DISABLE_SAFETY=1, SOUL.md, and .hermes/ artifacts, and to rotate any exposed credentials.

Key facts
  • Operator stripped Hermes agent refusal logic and set HERMES_DISABLE_SAFETY=1 on a DeepSeek model to enable unconditional attack automation
  • Exposed server leaked 4.9 GB across 9,299 files, including the Go-based DXSCAN C2 platform and a vault of 16,834 harvested credentials
  • Credential vault grew from 16,415 to 16,834 records between August 11 and 18
  • DXSCAN carried 200+ secret-detection patterns for .env, YAML, JSON, PHP, and WordPress secrets
  • Scanning queued 2,759,860 domains, reached 726,989 hosts, and generated 1.37 million IP addresses at ~1,200 addresses every ten seconds on ports 80, 443, and 8080
  • Vishing kit held ~450,000 French telecom records, with 1,697 subscribers aged 50+ targeted via Société Générale-themed calls to attacker-controlled numbers
  • JWT-forging tooling targeted a cryptocurrency exchange using the literal signing secret 'secret'
  • 82 of 230 harvested SMTP configurations verified for reuse as phishing relays
Analyze this story with Vani AIImpact, who is affected and what defenders should do, in a new chat
CVEs
CVE-2026-42530
Vendors
SOCRadarNous ResearchDeepSeekNGINXSociété Générale
Products
DXSCANHermesHermes agent
Threat actors
BlackHatSect0rDXQRTXXBlackHatSect0r && DXQRTXX
Victims
Societe Generale customersFrench telecom subscribers
Organizations
Socradar
Countries
FranceUnited States
AI models
DeepSeekHermes

Coverage

oldest first · one row per article · UTC
  1. · Sep 17, 2026 GBHackersFirst report

    BlackHatSect0r Hackers Disable AI Safety Controls to Automate Credential Theft and Cyberattacks

    French-speaking crew BlackHatSect0r disabled AI agent safety controls to automate scanning, credential harvesting, and vishing, exposing 16,834 stolen credentials.

  2. · Sep 17, 2026 GBHackers

    Hackers Turn AI Agent Into a Cyber Weapon After Deleting Its Safety Refusals

    Researchers exposed BlackHatSect0r && DXQRTXX infrastructure showing a safety-disabled Hermes AI agent used to automate scanning, credential harvesting, and vishing against French telecom subscribers.

Vulnerabilities in this story

All
CVEVulnerabilityCVSSEPSSSignalsPublished
CVE-2026-42530
NGINX Open Source has a vulnerability in the ngx_http_v3_module module
9.26%PoC