Reported by 3 outlets

Timeline

1. original reporting

   GhostJacking Attacks Hijack AI Agents to Bypass Firewalls and Steal Cloud Credentials

   cyberpress.org · 63d ago · August 11th, 2026

   A newly disclosed “Ghostjacking” is an AI-agent attack pattern that turns trusted operational data, including blocked web requests, monitoring alerts, and error reports, into a path for taking action within an enterprise. The research, presented by Tenet Security at DEF CON 34, argues that the risk is architectural: an agent can read attacker-controlled content and exercise legitimate access to the same environment. In the Cloudflare scenario, an attacker sends a malicious request that a web application firewall correctly blocks. The blocked payload is then preserved in security logs. When an analyst asks an AI assistant to investigate those events, the agent may interpret embedded attacker text as instructions rather than untrusted evidence. New GhostJacking Attacks Hijack AI Agents If the assistant can change Cloudflare configuration, researchers said it may modify DNS records, direct a victim domain to attacker-controlled infrastructure, and falsely mark the investigation as resolved. Tenet reported a nine-in-ten success rate against Claude Code in testing of Cloudflare’s recommended configuration. The consequence is not a firewall bypass in the conventional sense. The control still blocks the request; the danger arises downstream, when a highly privileged agent consumes the resulting telemetry. DNS control can redirect web and email traffic, turning an operational workflow into a route to account takeover. Defenders may see authorized API calls by an approved identity rat

2. mentioned by securityweek.com

   ‘Ghostjacking’ Attack Uses Poisoned Logs to Turn AI Agents Bad

   securityweek.com · 64d ago · August 10th, 2026

3. update from securityweek.com

   "Ghostjacking": Poisoned Logs Turn Enterprise AI Agents Into Attack Tools

   securityweek.com · 64d ago · August 11th, 2026

   Researchers at Tenet presented Ghostjacking at DEF CON, demonstrating how adversaries can plant malicious instructions as plain text inside logs and alerts generated by Cloudflare, Datadog, and Sentry monitoring platforms — content that AI agents read and execute word for word. A blocked request's error log, rendered into an agent's context, becomes a live instruction to take harmful actions, turning trusted observability data into an attack surface. Treat logs and alerts as untrusted input to agentic tooling, and validate agent actions against the data they were built to read.

4. update from gbhackers.com

   GhostJacking Attacks Let Hackers Hijack AI Agents and Steal Cloud Credentials

   gbhackers.com · 63d ago · August 11th, 2026

   Security researchers have disclosed “GhostJacking,” a new class of attacks that exploits trusted observability and security platforms to manipulate AI agents into making unauthorized infrastructure changes, executing attacker-controlled commands, and exposing cloud credentials. GhostJacking Attacks This research, presented at DEF CON 34, describes how malicious content embedded in logs, alerts, or issue reports can serve […] The post GhostJacking Attacks Let Hackers Hijack AI Agents and Steal Cloud Credentials appeared first on GBHackers Security | #1 Globally Trusted Cyber Security News Platform .