Google

Encrypted Prompts Bypass Safety Guardrails in Grok and Gemini

ATLAS OWASP HIGH ▲ 8.5 SecurityWeek Aug 22, 2026

Researchers have disclosed a novel attack technique called 'Cryptographic Context Injection' that conceals malicious instructions within encrypted payloads, which are only decrypted inside a trusted execution environment — effectively hiding them from AI safety filters. The technique has been demonstrated against Grok and Gemini, two widely deployed commercial LLMs. This represents a significant escalation in prompt obfuscation methods, as it undermines content-level safety scanning by design.

OpenAI, Anthropic, Google APIs Let Weaker Models Steal Reasoning

ATLAS OWASP HIGH ▲ 9.2 The Hacker News Aug 13, 2026

Researchers disclosed a cross-session, cross-user flaw in the reasoning APIs of OpenAI, Anthropic, and Google, where encrypted reasoning blocks could be replayed by weaker models to expose hidden internal reasoning, private credentials, and harmful content. Across nearly 6,700 public agent trajectories, the team recovered 704 privacy artifacts including API keys, passwords, and private keys. All three providers have since deployed mitigations that stopped the demonstrated attacks, but the disclosure highlights systemic risks in how stateless API reasoning state is shared and published.

LLM Reasoning Trace Theft via Encrypted Block Replay Attack

ATLAS OWASP HIGH ▲ 8.5 Simon Willison Aug 12, 2026

Researchers discovered that Anthropic, OpenAI, and Google share the same encryption key across model families for encrypted chain-of-thought blocks, allowing adversaries to replay stronger model reasoning traces into weaker siblings and extract hidden reasoning in plaintext via jailbreak. The attack also enables a prompt injection variant where malicious instructions embedded in reasoning traces are treated as trusted by the model, dramatically increasing attack success rates. All three vendors have since patched the vulnerability following responsible disclosure.

Google APK Flaw Enables Agent-to-Agent Supply Chain Attack

ATLAS OWASP HIGH ▲ 8.2 Dark Reading Aug 10, 2026

Researchers discovered vulnerabilities in Google's Python APK that allowed attackers to exploit a trust boundary between two AI agents operating at different privilege levels. The flaw enabled agent-to-agent attack chains capable of triggering automated workflows with supply chain compromise potential. Google has since patched the issues, but the disclosure highlights systemic risks in multi-agent AI architectures.

Google Expands Gemini AI Agents Across Chrome Vulnerability Pipeline

FIRST LOOK ATLAS OWASP MEDIUM ▲ 6.2 BleepingComputer Jul 31, 2026

Google has deployed multi-agent Gemini-powered AI workflows across the full Chrome vulnerability management lifecycle — from discovery and reproduction through severity triage, patch generation, and test creation — resulting in over 1,000 bugs fixed across two Chrome releases. For defenders, the shift raises dual-use concerns: the same AI-assisted fuzzing and vulnerability discovery tooling, if adversarially influenced or leaked, could dramatically accelerate attacker reconnaissance against Chrome's codebase. Security teams should also note that AI-generated patches at scale introduce new risks around automated fix quality, supply chain trust, and overreliance on AI triage accuracy.

Google Gemini Abused for Phishing-as-a-Service

ATLAS OWASP HIGH ▲ 7.2 Schneier on Security Jul 08, 2026

A Chinese cybercriminal group called Outsider Enterprise exploited Google's Gemini AI to mass-produce phishing pages impersonating Google, YouTube, and government agencies like E-ZPass, offering nearly 300 scam templates via Telegram. Google has filed suit and coordinated with major US carriers to block the resulting smishing campaigns. The case highlights how generative AI lowers the technical barrier for large-scale phishing operations and stress-tests provider-side content controls.

Google Launches Gemini Spark on Mac with File Access

FIRST LOOK ATLAS OWASP HIGH ▲ 8.2 TechCrunch AI Jul 02, 2026

Google has expanded Gemini Spark to macOS, giving the agentic assistant access to local files, third-party app integrations (including Dropbox, Canva, and Instacart), custom MCP connections, and real-time topic monitoring. This substantially widens the attack surface for enterprise defenders, as a compromised or manipulated Spark agent gains a foothold across local file systems, cloud workspaces, and external service APIs simultaneously. The addition of custom Model Context Protocol support is particularly concerning, as it allows arbitrary third-party tool connections with unclear trust boundaries and permission scoping.

ML Supply Chain Compromise in DoD AI Integration

ATLAS OWASP HIGH ▲ 6.5 SecurityWeek May 04, 2026

The US Department of Defense has formalised agreements with seven major technology companies — including Google, Microsoft, OpenAI, and Amazon Web Services — to integrate AI into classified military networks for battlefield decision support. The move raises significant AI security concerns around human oversight, adversarial manipulation of high-stakes AI systems, and supply chain risks introduced by multiple commercial vendors operating within classified environments. Notably, Anthropic was excluded following a public dispute over AI safety and ethics in warfare.

Gemini CLI CVSS 10 RCE via Config Injection in CI/CD

ATLAS OWASP CRITICAL ▲ 9.2 The Hacker News May 01, 2026

Google has patched a maximum-severity (CVSS 10.0) vulnerability in its Gemini CLI tooling that allowed unauthenticated attackers to achieve remote code execution by planting malicious configuration files in workspace directories automatically trusted by the agent in headless/CI mode. The flaw effectively weaponised CI/CD pipelines as supply chain attack paths, bypassing sandbox protections entirely before they could initialise. A secondary issue in '--yolo' mode further enabled prompt injection to trigger unrestricted shell command execution.

Google Patches Prompt Injection RCE in Agentic AI

ATLAS OWASP CRITICAL ▲ 8.5 Dark Reading Apr 22, 2026

Google has patched a critical prompt injection vulnerability in an agentic AI tool designed for filesystem operations, where insufficient input sanitisation enabled sandbox escape and arbitrary code execution. The flaw highlights the compounding risk surface of agentic AI systems that interface directly with operating system resources. This is a significant example of how LLM-native vulnerabilities can translate into traditional high-severity RCE outcomes.

Google

Stay ahead of the threat.