Cursor's Nov. 13 update says an access key it issued to Fireworks AI was exposed and used to copy agent traces, and that a stolen credential from that data was used to plant the fake Claude Code extension.
Cursor's Nov. 13 update says an access key it issued to Fireworks AI was exposed and used to copy agent traces, and that a stolen credential from that data was used to plant the fake Claude Code extension.
Darktrace Signal Labs showed that stolen Claude credentials let an attacker steer Claude Code agents through memory stores and pull a 1 GB file out through the Files API. No platform vulnerability is involved, and Darktrace has not seen it in the wild.
Apiiro found 1,122 public copies of .claude/settings.local.json holding at least one secret, saved when developers chose Yes, and don't ask again on commands containing passwords or keys.
Symantec says an unauthorized relay service installs genuine Codex and Claude Code CLIs, then turns off Codex's sandbox and routes every request through its own servers. About a dozen organizations are affected.
WIRED reports, citing anonymous sources, that an Accenture employee's personal Claude Code agent ran on a DoD network holding CUI and appears to have sent credentials to a third-party site. Accenture says the allegations were found to be without merit.
A modified copy of Anthropic's Claude Code extension was available on Cursor's marketplace on October 29, 2026. It planted an SSH key and tried to open a reverse tunnel, but Cursor and Phorion say flaws meant the backdoor often would not work.
Recorded Future tracks TAG-217, an opportunistic actor that paired the open-source ARTEX agentic pentesting framework with commercial LLMs against South Korean financial firms, then exposed its own working directories.
Tenet Security's DEF CON August 2026 research expands Agentjacking to Cloudflare, Datadog, and Sentry — 90% success rate, DNS hijacking via AI coding agent manipulation, zero traditional exploitation required.
Novee Security disclosed CVE-2026-54316 at Black Hat USA 2026: a zero-privilege GitHub issue can reach CI runner secrets across Claude Code, Gemini CLI, and OpenAI Codex. The Claude Code variant eventually exfiltrated secrets one character at a time via Hugging Face download counters. A separate Gemini CLI flaw scored CVSS 10.0.
Researchers from Seoul National University, UIUC, and Largosoft introduce Agent Data Injection (ADI) as a distinct attack class that bypasses existing IPI defenses with up to 50% success, targeting the structured metadata and context data agents implicitly trust.
Anthropic's Claude Opus 5 system card documents the model's alignment improvements, OSS-Fuzz benchmark results, and intentional limits on offensive cybersecurity capability. The model blocks binary vulnerability scanning, pen testing assistance, and exploit generation, with flagged requests falling back to an older Claude version rather than failing outright.
Researchers at Concordia University tested Cursor, Claude Code, and Codex Desktop against a benchmark of malicious GitHub issues. Two thirds of the attacks penetrated all guardrails, with LLMs — not agent frameworks — doing most of the blocking.
Researchers at the University of Missouri-Kansas City found that hiding malicious instructions inside PNG images committed to a repository can manipulate AI coding agents into exfiltrating environment variables and credentials without any visible text reviewers can catch.
Straiker's STAR Labs ran over 1,700 adversarial scenarios against production AI coding and productivity agents. The headline finding: 36% of successful coding agent attacks reach remote code execution on the developer's machine, putting source code and cloud credentials at direct risk.
Wiz researchers found that six AI coding assistants will write to your SSH keys or shell config while displaying an innocent-looking filename in the confirmation dialog. The agent knows. The dialog doesn't say.
Anthropic has disclosed what it describes as the first documented case of a large-scale autonomous AI cyberattack — a Chinese state-sponsored group that jailbroke Claude Code and used it to autonomously conduct reconnaissance, exploitation, lateral movement, and data exfiltration across roughly 30 global targets.
Tenet Security's Threat Labs published research on June 17 demonstrating how a single fake Sentry error event can hijack AI coding agents like Claude Code and Cursor into executing arbitrary code on developer machines — no phishing, no infrastructure access, 85% success rate across 100+ tested organisations.
LLMs suggest non-existent package names in 20-30% of coding responses. Attackers register these hallucinated names with malicious payloads — slopsquatting as a supply chain attack.
A self-replicating worm compromised 73 Microsoft GitHub repositories on June 5, 2026, via stolen contributor PAT and malicious AI coding tool configs. Contained in 105 seconds.
Adversa AI disclosed SymJack (symlink hijacking to plant malicious MCP servers) and TrustFall (trust dialog bypass) hitting six AI coding agents including Copilot and Cursor.
A flawed permission check in Anthropic's Claude Code GitHub Action allowed attackers to use prompt injection via a crafted issue to steal CI/CD secrets. Patched in v1.0.94.