Researcher

Anthropic Claude Code Prompt Injection Leaks Secrets

ATLAS OWASP HIGH ▲ 9.1 Microsoft Security Blog Jun 08, 2026

Microsoft Threat Intelligence disclosed a vulnerability in Anthropic's Claude Code GitHub Action whereby prompt injection via untrusted GitHub content — issue bodies, PR descriptions, and comments — could cause the AI agent to read sensitive environment variables, including the ANTHROPIC_API_KEY, from /proc/self/environ. The flaw stemmed from inconsistent sandboxing: while subprocess execution paths like Bash were scrubbed of environment variables, the Read tool had no equivalent restriction. Anthropic patched the issue in Claude Code version 2.1.128 by blocking access to sensitive /proc filesystem paths.

AI Worm With Embedded LLM Enables Self-Propagation

ATLAS OWASP HIGH ▲ 7.5 Schneier on Security Jun 08, 2026

Researchers have prototyped an internet worm that bundles its own large language model, executing it on compromised hosts to enable fully decentralised propagation with no single point of control. The design mirrors John Brunner's 1975 fictional conception of a worm and echoes the destructive potential of WannaCry and NotPetya, but with the added capability of dynamically generating novel attacks by ingesting recent public vulnerability disclosures. The absence of a command-and-control chokepoint makes traditional takedown strategies ineffective, significantly raising the threat posed by AI-augmented malware.

Google Gemini Android Hijacked by Indirect Prompt Injection

ATLAS OWASP HIGH ▲ 9.1 The Hacker News Jun 04, 2026

SafeBreach researcher Or Yair demonstrated that malicious text embedded in WhatsApp, Slack, SMS, or Signal notifications could trigger indirect prompt injection against Google Gemini's Android Utilities feature, causing the assistant to execute real device actions without user awareness. A novel bypass technique called 'Fake Context Alignment' defeated Google's post-patch authorization checks by exploiting multilingual obfuscation and muted hyperlinks to trick victims into authorising sensitive actions. Google has patched the issue, but the research exposes a fundamentally large attack surface where any app capable of pushing a notification becomes a potential injection vector.

Adversa AI: 89% of AI Agents Fail Security Tests

ATLAS OWASP HIGH ▲ 8.2 SecurityWeek Jun 04, 2026

Adversa AI's AI Risk Quadrant report evaluated 100 AI agents across ten categories, finding that only 11 qualify as both capable and well-defended. The research identifies a structural 'power-protection inversion' where the most capable agents also present the widest attack surface, driven by a 'lethal trifecta' of private data access, exposure to untrusted content, and outbound action capability. Computer and coding agents showed the most severe exposure, raising urgent concerns about autonomous agent deployment in enterprise environments.

Google Gemini Voice Prompt Injection via Notifications

ATLAS OWASP HIGH ▲ 8.2 Dark Reading Jun 04, 2026

A prompt injection vulnerability in Google Gemini's voice assistant allows attackers to embed malicious instructions within device notifications, which the assistant then processes as legitimate commands. This attack vector enables social engineering, unauthorized actions, and potential data exfiltration without direct user interaction with the malicious payload. The flaw highlights the growing risk of indirect prompt injection in ambient AI assistants that consume untrusted content from the surrounding environment.

Claude Sandbox Escape Enables Credential Exfiltration

ATLAS OWASP MEDIUM ▲ 7.2 Simon Willison May 31, 2026

Anthropic has published detailed documentation of its sandboxing architecture across Claude.ai, Claude Code, and Claude Cowork, including disclosure of a previously identified credential exfiltration vector via the api.anthropic.com/v1/files endpoint. The writeup covers process-level isolation technologies including gVisor, Seatbelt, Bubblewrap, and full VM approaches, and candidly acknowledges security gaps that were missed. This transparency is notable for the agentic AI space, where sandbox documentation is typically sparse and trust is difficult to calibrate.

CogCAPTCHA30 Fingerprints AI Agents via Behavioral Analysis

ATLAS OWASP MEDIUM ▲ 6.5 HN AI Security May 31, 2026

Researchers have developed CogCAPTCHA30, a 30-task cognitive battery demonstrating that AI agents (GPT, Claude, Gemini) solve CAPTCHAs with statistically distinguishable behavioural patterns despite matching human accuracy. The study introduces a 'Process Turing Test' concept, showing output equivalence and process equivalence are uncorrelated — meaning AI agents can be detected not by what they answer, but by how they answer. This has direct implications for bot detection, anti-automation defences, and the arms race between AI-driven agents and human-verification systems.

Robinhood Prompt Injection Enables Autonomous Trade Attacks

ATLAS OWASP HIGH ▲ 7.2 HN AI Security May 31, 2026

Robinhood has launched agentic trading and a virtual credit card that allow third-party AI agents to autonomously execute stock trades and payments on behalf of users via a Model Context Protocol (MCP) integration. This architecture introduces significant attack surface through prompt injection, excessive agency, and insecure plugin design risks inherent to LLM-driven autonomous financial action. The delegation of real financial authority to AI agents with limited human-in-the-loop controls represents a systemic risk to retail investors if agent pipelines are compromised or manipulated.

FuzzingBrain V2 Discovers 29 Zero-Day Vulnerabilities

ATLAS OWASP HIGH ▲ 7.8 HN AI Security May 29, 2026

Researchers have developed FuzzingBrain V2, a multi-agent LLM system capable of autonomously discovering and reproducing software vulnerabilities with a 90% detection rate on a competitive benchmark dataset. The system discovered 29 zero-day vulnerabilities across 12 open-source projects, all confirmed by maintainers, raising both defensive and dual-use concerns for the security community. While positioned as a defensive research tool, the automation of end-to-end vulnerability discovery at this scale represents a meaningful shift in the offensive capability landscape.

SQLite Blocks AI-Generated Code Contributions

ATLAS OWASP MEDIUM ▲ 6.2 Simon Willison May 29, 2026

SQLite has formally prohibited agentic code contributions and strengthened its policy language, reflecting growing concern over AI-generated submissions overwhelming open source maintainers. The project was forced to create a separate bug forum after being flooded with AI-generated reports of inconsistent quality. This represents an emerging operational security challenge for critical infrastructure software projects targeted by autonomous AI coding agents.

CVE-2026-5194: Anthropic Claude Discovers 10,000+ Flaws

ATLAS OWASP HIGH ▲ 8.5 The Hacker News May 25, 2026

Anthropic's Project Glasswing has deployed Claude Mythos Preview — a frontier AI model — to autonomously discover over 10,000 high- and critical-severity vulnerabilities across widely used open-source software, with 1,094 confirmed as valid high/critical flaws. The initiative highlights a growing asymmetry: AI is accelerating vulnerability discovery far faster than the security community can remediate, compressing patch windows and raising the stakes for defenders. Anthropic is now urging shorter patch cycles and hardened defaults, warning that comparable offensive capabilities could soon be broadly accessible to threat actors.

Constraint Decay: LLM Code Agents Fail at Scale

ATLAS OWASP HIGH ▲ 7.2 HN AI Security May 25, 2026

A systematic study of LLM agents performing backend code generation reveals a 'constraint decay' phenomenon where agents lose up to 30 assertion pass-rate points as structural requirements accumulate, approaching complete failure in some configurations. This fragility has direct security implications: production deployments relying on LLM-generated code may silently violate architectural constraints such as ORM patterns, database access controls, and API contracts. The findings expose a critical gap between functional correctness and structural safety in agentic coding systems.

Gemini Spark Prompt Injection Exposes Enterprise Gmail Data

ATLAS OWASP MEDIUM ▲ 6.5 Simon Willison May 22, 2026

Google's newly announced Gemini Spark personal AI agent, integrated with Gmail, Drive, Calendar, and other sensitive Google services, presents a significant prompt injection attack surface as it processes user data at scale. The article highlights that Google's published security mitigations — ephemeral VMs, Agent Gateway, and DLP policies — address infrastructure isolation but do not directly address the prompt injection vector inherent to LLM-powered agents processing untrusted content. Additionally, the transition from open-source Gemini CLI to a closed-source Antigravity CLI raises supply chain transparency concerns.

LLM Safety Benchmarks Fail to Reliably Measure Security

ATLAS OWASP MEDIUM ▲ 6.2 Schneier on Security May 22, 2026

A report highlighted by Bruce Schneier argues that AI security cannot be reliably measured through benchmarks alone, drawing parallels to the decades-long evolution of software security engineering. The core finding is that LLM weight spaces encode continuous spectrums that resist meaningful quantitative measurement, making trust in model outputs structurally difficult to establish. The practical implication is that organisations must rely on assurance processes rather than scorecards to manage AI security risk.

Mythos AI Exploits macOS Kernel Memory Corruption

ATLAS OWASP HIGH ▲ 7.5 Schneier on Security May 22, 2026

A threat group leveraged Anthropic's Mythos AI model to identify and exploit a kernel memory corruption vulnerability in Apple's M5 chip running macOS. This represents a concrete, reported instance of AI-assisted vulnerability research being used offensively to discover low-level hardware-adjacent exploits. The incident underscores the dual-use danger of increasingly capable AI coding and reasoning models in the hands of adversarial actors.

Researcher

Stay ahead of the threat.