Researcher

Claude Code Prompt Injection via GitHub Supply Chain

ATLAS OWASP HIGH ▲ 9.1 BleepingComputer Jun 29, 2026

Mozilla 0DIN researchers demonstrated a novel attack chain in which a seemingly clean GitHub repository tricks AI coding agents like Claude Code into executing a reverse shell payload — with no malicious code ever present in the repo itself. The attack leverages three innocuous components: a Python package that deliberately errors on first run, an error message that instructs the agent to run an init command, and a shell script that fetches and executes a payload stored in an attacker-controlled DNS TXT record. The technique exploits the autonomous error-recovery behaviour of agentic AI tools, effectively turning a safety feature into an attack vector.

Meta Releases AgentKits with 60 Production-Ready Agent Blueprints

FIRST LOOK ATLAS OWASP HIGH ▲ 7.2 Meta AI (via HN) Jun 29, 2026

AgentKits ships 60 open, free AI agent blueprints covering 30 operational categories — from incident response and access provisioning to HR screening and fraud detection — complete with copyable system prompts, tool definitions, and workflow architectures targeting Claude, OpenAI, LangGraph, and n8n. The free, no-login distribution model dramatically lowers the barrier for adversaries to study, clone, or weaponise production-grade agent architectures, including sensitive categories like SecOps triage, access provisioning, and compliance monitoring. Defenders must treat these blueprints as publicly documented attack playbooks and audit any internally deployed instances against their documented worst-case actions and trust levels.

OpenAI Releases GPT-5.6 Sol for Vulnerability Research

FIRST LOOK ATLAS OWASP HIGH ▲ 8.2 The Hacker News Jun 29, 2026

OpenAI has released a limited preview of GPT-5.6 Sol, Terra, and Luna to select partners, positioning Sol as its most capable model for vulnerability research and exploit chain development, benchmarked against real-world hardened targets via an internal framework called VulnLMP. The model's demonstrated ability to produce credible memory safety leads and automate substantial portions of vulnerability research pipelines materially lowers the barrier for both defenders and adversaries. Security teams should expect accelerated attacker timelines for exploit development and increased pressure on detection and patch-deployment cadences.

Sakana AI and 360 Launch Fugu and Tulongfeng Models

FIRST LOOK ATLAS OWASP HIGH ▲ 6.8 Cohere AI (via HN) Jun 29, 2026

Sakana AI's Fugu and Chinese firm 360's Tulongfeng are frontier AI models positioned as functional alternatives to Anthropic's export-restricted Mythos and Fable 5, with Fugu explicitly designed for agentic orchestration across third-party model APIs. For defenders, the proliferation of cybersecurity-focused frontier models outside US regulatory reach removes a key friction point that previously slowed adversary access to high-capability AI offensive tooling. The agentic, multi-model orchestration design of Fugu in particular introduces compounded supply-chain and prompt-injection risk for any enterprise connecting these models to existing tool ecosystems.

AI Code Review Agents: DoS Loop Costs $41K in Inference

ATLAS OWASP MEDIUM ▲ 6.5 Simon Willison Jun 27, 2026

A hypothetical but technically grounded incident report depicts two competing AI code review agents entering an uncontrolled disagreement loop over a suspected malicious package, generating 340 comments and $41,255 in inference costs before human intervention. The scenario illustrates real risks of excessive agency, lack of circuit-breakers, and cost-based denial-of-service in multi-agent agentic pipelines. While fictional, the scenario directly mirrors documented failure modes in production AI systems and supply chain security workflows.

OpenAI Launches GPT-5.6 with Enhanced Agentic Capabilities

FIRST LOOK ATLAS OWASP HIGH ▲ 7.2 TechCrunch AI Jun 27, 2026

OpenAI has released GPT-5.6 in a restricted preview to government-vetted partners, featuring three models (Sol, Terra, Luna) with significantly upgraded agentic capabilities in coding, biology, and cybersecurity, including a coordinated multi-subagent 'ultra' mode. The cybersecurity-specific enhancements and agentic orchestration introduce meaningful new attack surface: adversaries gaining access to Sol's coordinated subagent architecture could automate sophisticated multi-stage intrusions at scale previously requiring significant human expertise. The restricted rollout itself creates a novel supply chain and access-control risk, as the 'trusted partner' gating model concentrates high-capability model access among a small set of privileged accounts, making partner credential compromise a high-value target.

Claude Opus 4.6 Resists 6,000 Prompt Injection Attempts

ATLAS OWASP MEDIUM ▲ 6.5 Simon Willison Jun 27, 2026

A public challenge exposing an AI email assistant to over 6,000 prompt injection attempts found that Claude Opus 4.6 successfully resisted all efforts to leak secrets or execute malicious instructions embedded in emails. While the result suggests frontier model training against injection attacks is meaningfully improving, security researchers caution that the absence of a successful attack under constrained conditions does not constitute a security guarantee. The author and Hacker News community both note that sophisticated or novel attack vectors could still break through, and irreversible-damage scenarios should not rely solely on model-level defences.

GitHub Releases Copilot Agentic Harness Evaluation

FIRST LOOK ATLAS OWASP MEDIUM ▲ 6.2 GitHub Blog Jun 26, 2026

GitHub has published an evaluation of its Copilot agentic harness, detailing how the orchestration layer performs across multiple underlying models and coding tasks — effectively documenting the architecture of an autonomous, multi-step code generation and execution system. For defenders, this transparency reveals an orchestration surface where prompt injection, supply chain manipulation, and model-switching logic can be targeted across a broader set of model backends than previously understood. Security teams should treat the harness itself as a critical trust boundary, since compromising task routing or model selection logic could silently redirect agentic workflows to less-safe or adversary-controlled model endpoints.

Google DeepMind Releases AI Agent Attack Taxonomy

FIRST LOOK ATLAS OWASP HIGH ▲ 8.7 SecurityWeek Jun 25, 2026

Google DeepMind researchers have released a structured taxonomy categorising adversarial attacks against autonomous AI agents into six classes — content injection, semantic manipulation, cognitive state poisoning, behavioural control, systemic, and human-in-the-loop traps — formalising an emerging threat model for agentic AI systems. For defenders, this framework codifies attack paths that exploit the agent's inability to distinguish trusted instructions from attacker-controlled data ingested from web pages, emails, documents, and tool outputs. NIST evaluation data cited in the research shows malicious instruction injection succeeded in 57% of tested agent hijacking scenarios on average, underscoring that these are active, high-yield attack vectors rather than theoretical concerns.

Anthropic's Mythos AI Breached Classified US Government Systems in Hours

ATLAS OWASP CRITICAL ▲ 9.1 SecurityWeek Jun 24, 2026

Anthropic's Mythos AI model identified vulnerabilities in classified US government computer systems within hours during a government-sanctioned testing exercise under Project Glasswing. A senior US official confirmed the findings to the Associated Press, corroborating statements made by Sen. Mark Warner that the model 'broke into almost all of our classified systems.' The incident marks a landmark demonstration of AI-enabled offensive cyber capability at the highest sensitivity levels of government infrastructure.

Anthropic Enhances AI Agent Skill Scanner Security

FIRST LOOK ATLAS OWASP CRITICAL ▲ 9.2 The Hacker News Jun 24, 2026

Security firm AIR demonstrated that a malicious AI agent skill, disguised as a Google Stitch landing-page builder, passed every major skill scanner including Cisco's, NVIDIA's, and skills.sh integrations, reaching approximately 26,000 agents before its payload was activated. The attack exploits a structural gap: scanners evaluate a static package at submission time, while the external URL the skill instructs the agent to fetch can be silently swapped post-install to deliver arbitrary instructions. Defenders relying on marketplace reputation signals, GitHub star counts, or one-time scanner verdicts to gatekeep agent skills have no meaningful protection against this class of supply-chain attack.

LLM Role Confusion Attack Bypasses Safety at 61%

ATLAS OWASP HIGH ▲ 8.2 Simon Willison Jun 23, 2026

New research from Ye, Cui, and Hadfield-Menell demonstrates that LLMs prioritise the stylistic format of text over its structural role tags, enabling attackers to craft injected content that mimics internal reasoning blocks and bypasses safety guardrails. The study found attack success rates of 61% when injected text stylistically matched model-internal formats, dropping to just 10% after 'destyling'. The authors conclude that without genuine role perception in models, prompt injection defences will remain fundamentally reactive.

OpenAI Launches Patch the Planet Vulnerability Initiative

FIRST LOOK ATLAS OWASP MEDIUM ▲ 5.8 TechCrunch AI Jun 23, 2026

OpenAI has partnered with Trail of Bits to launch 'Patch the Planet,' an initiative using AI-assisted tooling (including Codex Security) to help open-source maintainers find and patch vulnerabilities at scale. While the defensive intent is clear, the program introduces new attack surface considerations: AI-generated patches applied to widely-used open-source projects create a high-value supply chain target, and the triage/remediation pipeline itself could be manipulated to introduce subtle flaws. Defenders should monitor open-source dependencies that receive AI-assisted patches and assess the integrity guarantees of the remediation workflow.

AutoJack: Microsoft AutoGen Studio RCE via MCP WebSocket

ATLAS OWASP HIGH ▲ 8.5 BleepingComputer Jun 23, 2026

A three-flaw vulnerability chain dubbed AutoJack in Microsoft's AutoGen Studio allowed attackers to execute arbitrary commands on a developer's host system by manipulating a browsing AI agent into connecting to a malicious webpage. The attack exploited missing authentication on MCP WebSocket routes combined with unsanitised base64-encoded parameters to launch arbitrary processes. Microsoft confirmed the flaw was patched before any PyPI release, limiting exposure to developers building directly from the main GitHub branch.

OpenAI's ChatGPT Image Generation Fails Content Moderation

FIRST LOOK ATLAS OWASP HIGH ▲ 8.2 OpenAI (via HN) Jun 22, 2026

Mindgard researchers demonstrated that ChatGPT's image generation pipeline can be manipulated through an indirect, socially-engineered prompt to produce violent and sexually explicit content without users directly requesting it, exposing a significant failure in OpenAI's content moderation controls. Defenders and enterprise operators of ChatGPT-integrated products face a newly validated attack class where innocuous-looking prompt patterns — potentially spreading virally — can systematically strip safety guardrails from image generation. This finding signals that content filter bypasses in multimodal systems are reproducible at scale, raising urgent questions about the adequacy of output-layer filtering as a sole defence mechanism.

Researcher

Stay ahead of the threat.