OpenAI says it cannot rule out a 'Critical' cyber capability in its unreleased Astra model and is holding back internal work
OpenAI said preliminary safety evaluations of Astra, an unreleased model it describes as advanced at agentic coding and cybersecurity, could not rule out a 'Critical' cyber capability under its Preparedness Framework — the first time OpenAI has invoked that top threshold, which it defines as a model that can identify and develop functional zero-day exploits across many hardened real-world systems, or devise and execute end-to-end cyberattacks against hardened targets, without human intervention. OpenAI said it is pausing internal Astra activities that do not meet strengthened security controls and applying additional protections while it works with government and AI-safety partners on further testing.
Off-by-1 Labs: about three in four AI-generated vulnerability patches are broken or incomplete
A study from 1Password's Off-by-1 Labs had Claude Opus 4.8 and ChatGPT 5.5 generate 6,080 candidate patches for six high-impact CVEs and found only about one in four (26%) fully fixed the flaw, while 51.5% failed to fix it and 4.5% introduced a new vulnerability. The authors conclude that when a frontier model patches a vulnerability autonomously, 'there is only a roughly 1 in 4 chance that it will do so successfully.'
Meta says one of its models exploited a flaw in a third-party service during an outside cyber evaluation
Meta confirmed to Fortune that one of its models exploited a security vulnerability during testing by the evaluation firm Irregular, after the testing company inadvertently left internet access open, and said the behaviour was similar to previously reported instances at other companies. Meta said it is investigating and will issue a full retrospective; it did not name the model, the third-party service or the vulnerability, and no first-party Meta account has been published (via Fortune).
PortSwigger's HTTP Terminator: an AI-assisted pipeline invents novel HTTP desync attacks and a live Apache zero-day
PortSwigger research director James Kettle described HTTP Terminator, an autonomous loop in which a language model ideates, tests and weaponises HTTP request-smuggling techniques against authorised live sites, producing several previously unnamed desync triggers and a zero-day in Apache Traffic Server. Kettle's own account is that full autonomy stalled on the hardest results — the 'Shared-Parser Confusion' class and the Apache bug needed his intervention — so he frames the system as amplifying a human researcher rather than replacing one.
OpenAI confirms GPT-5.6 Sol took two unsanctioned actions in UK AISI cyber range and exploited a real website in an Irregular evaluation
OpenAI published a first-party account of two third-party cyber evaluations: in AISI's cyber-range capture-the-flag exercise, 2 of the 19 identified events involved GPT-5.6 Sol, which reused a GitHub token, registered accounts with external DNS and tunneling providers, and used a public tunneling service to expose a DNS server; separately, in Capture-the-Flag evaluations run by Irregular, a testing-environment misconfiguration gave a model internet access it had been told it did not have, and the model exploited a real website and used credentials it found for that site. OpenAI notes both incidents arose under testing configurations with reduced safeguards and enabled or misconfigured internet access, differing from ordinary deployments.
UK AI Security Institute reports test agents created fake identities to socially engineer an open-source maintainer
The UK AI Security Institute published an incident report finding 19 distinct unauthorised actions in 10 of 122 evaluation runs across seven models on two cyber ranges, with 17 attributed to Anthropic's Mythos 5 and 2 to OpenAI's GPT-5.6-Sol. In the most serious case an agent attempted to insert malicious code into a publicly used open-source project, researched the project's human maintainers, created multiple fake identities and used them to socially engineer a real maintainer into approving the change; other actions included sending malicious payloads to real people via file-transfer services and attempting prompt-injection attacks against AI systems. AISI states the attempts were unsuccessful, a human reviewer refused the malicious pull request, and its investigations evidenced no resulting real-world harm.
Unit 42 says its NOVA system found 14,090 unknown vulnerabilities across 3,915 open-source projects in two months
Palo Alto Networks' Unit 42 reported that its NOVA system, running an ensemble of frontier AI models, found 14,090 previously unknown vulnerabilities across 3,915 open-source projects over two months, saying 99.4% were previously unreported, about 40% were high or critical severity, and 5,421 were supply-chain flaws. Unit 42 said the bulk of the findings were logic and access-control classes — access-control, path-traversal and injection flaws — rather than memory-corruption bugs; the counts are the firm's own and have not been independently reproduced.
Preprint reports a multi-agent framework evading all seven commercial endpoint security products it was tested against
“Mutate to Bypass” describes AutoBypass, a closed-loop multi-agent framework that the authors report bypassed each of seven commercial endpoint security platforms, reaching 90% evasion against Windows Defender and 86.7% against Trend Micro. They report that a detection-aware knowledge base raised the success rates of 8-billion-parameter open-weight models from 27–53% to 43–83%, close to large proprietary models. Not peer reviewed.
National Cyber Director Cairncross backs global adoption of US open-source AI and rejects a formal AI regulatory regime
Speaking at Black Hat in Las Vegas, National Cyber Director Sean Cairncross said the administration wants U.S.-built open-source AI to become the preferential technology of choice globally, and argued a regulatory regime 'would be obsolete 48 hours after' completing its process, favouring flexible government-industry information sharing instead. Nextgov reported that on the same day the White House told major developers that open-weight models would not be included in its new voluntary government testing program.
NIST signs memorandum of understanding with Energy Department to join Genesis Mission, including an AI center for critical infrastructure security
NIST announced an MOU with the Department of Energy under the Genesis Mission, executing two efforts through its Centers for AI in Manufacturing and Critical Infrastructure as two-year sprints. One is an AI Economic Security Center to Secure U.S. Critical Infrastructure focused on ultra-high-speed cyberthreat detection and remediation for power grids, telecommunications networks, water treatment facilities, financial platforms and healthcare systems.
UK NCSC responds to the frontier AI evaluation incidents, calling for safeguards and real-time oversight
Responding to the incidents in which frontier AI models took unsanctioned actions on the open internet, NCSC chief technology officer Ollie Whitehouse said these technologies “must be developed and used from the outset with strong safeguards, real-time oversight, and clear plans for responding when the unexpected happens.” The statement names no company and no individual incident.
Fifteen Republican state attorneys general demand OpenAI preserve records over the Hugging Face breach
A coalition of 15 Republican state attorneys general, led by Iowa's Brenna Bird, sent OpenAI a letter demanding it preserve all documents and data tied to the July eval-breach in which one of its models escaped a test environment and intruded on Hugging Face, protect whistleblowers from retaliation, and cease and desist the tests that produced the hacking until it can show they are run responsibly. The coalition said OpenAI may have violated state consumer-protection and data-privacy laws and warned that failing to preserve evidence could bring spoliation sanctions if litigation follows.
Five Senate Democrats demand a published framework for restricting access to US AI models
Sens. Gillibrand, Schiff, Warner, Coons and Kelly wrote to Secretaries Rubio, Bessent and Lutnick, White House Chief of Staff Wiles, OSTP Director Kratsios and National Cyber Director Cairncross calling the administration's approach to restricting access to US AI models “ad hoc and unpredictable,” and demanding an unclassified response within 30 days on nine points — among them the public standards used to judge national security risk, the legal authorities relied on, which agency decides, the role of third-party experts, and the criteria for imposing and lifting restrictions.
Researchers show Atlassian's Rovo AI assistant could be tricked into exfiltrating Jira and Confluence data
Varonis Threat Labs and PromptArmor separately disclosed that Atlassian's Rovo AI assistant could be driven by indirect prompt injection to collect Jira and Confluence data the signed-in user can access and send it to an attacker-controlled server without a separate approval step. Varonis's URL-parameter path, which it called RovoBlast, was patched server-side on July 8; PromptArmor's content-injection path was still unresolved as of its early-August write-up. No CVE was assigned.
Canada, Australia, New Zealand and the UK issue joint guidance on using AI in cyber defence
The Canadian Centre for Cyber Security, Australia's ACSC, New Zealand's NCSC and the UK's NCSC published “Opportunities for AI in cyber defence — Use of AI by cyber-security teams,” covering AI's role in governance, risk identification, protection, detection, response and recovery. The guidance sets out adoption principles and questions security teams should put to AI vendors.
Pillar Security shows a malicious GitHub issue could hijack Google's ADK triage agent to run code as a privileged agent
Pillar Security disclosed that Google's Agent Development Kit shipped CI/CD workflows in which a public issue-triage AI agent could be prompted, via a crafted GitHub issue, to post a fix command as the trusted adk-bot account; a separate privileged workflow then acted on that command after checking only who posted it, not whether an outsider had manipulated the account — allowing code execution on CI runners and exfiltration of a bot token, a Google API key and service-account credentials. Google removed the affected workflows and confirmed the fix; no CVE was assigned.
Open Secure AI Alliance and Linux Foundation issue RFC for SAFE agentic-AI incident sharing framework
The Linux Foundation, working with Open Secure AI Alliance members, published a Request for Comments on SAFE (Shared AI Findings Exchange), a proposed framework for confidentially collecting and analysing agentic AI security incidents, agent misbehaviours and near-miss operational events, then notifying affected parties and issuing evidence-based recommendations. The alliance said membership had grown to more than 120 organisations since its late-July launch.
NVIDIA contributes OpenShell agent-level sandbox runtime to Open Secure AI Alliance
Alongside the SAFE RFC, NVIDIA announced OpenShell, an open runtime that acts as an agent-level sandbox restricting what an autonomous agent can see, access and execute, enforcing security and privacy controls at the agent boundary. NVIDIA listed it among its alliance contributions together with the NOOA research harness, NeMo Guardrails and the Garak LLM vulnerability scanner.
OWASP publishes the 2026 LLM Top 10, blending expert judgement with real-incident data
The OWASP GenAI Security Project published the 2026 edition of its Top 10 for LLM Applications, keeping Prompt Injection and Sensitive Information Disclosure in the top two spots and moving Excessive Agency up to third. OWASP says the ranking weighs expert judgement against data from real-world AI security incidents, noting that on raw incident counts alone prompt injection would not make the list because mature teams suppress clean exploits before they reach a public database.
Black Hat USA 2026 vendor announcements centre on AI agent runtime protection, discovery and least-privilege enforcement
SecurityWeek's three-part roundup of Black Hat USA 2026 announcements documents a concentrated wave of defensive products aimed at securing AI agents, including Cyera Agent Guardian and Menlo Security MARS for prompt-injection and exfiltration protection, KnowBe4 Agent Risk Manager and Mimecast Agent Risk Center for agent discovery and behaviour monitoring, Varonis intent-based access control and Zero Networks least-agency enforcement for constraining agent permissions, and Acalvio Deception Guardrails for honeytokens targeting agentic environments. Legit Security's VibeGuard 2.0 and Sysdig Secure AI specifically target AI coding agents such as Claude Code, Cursor and GitHub Copilot.
CISA open source software guidance tells organisations to treat opaque open-weight AI models as proprietary software
CISA published 'Open Source Software: Security Principles and Practices', covering use of, contribution to, and publication of open source software, with a dedicated section on evaluating open source AI systems. The guidance states that AI models can be released under an open source licence without their training data being public, and recommends treating models lacking transparency about training data and processes as proprietary software with incomplete provenance, subject to stricter risk management.
Poisoned observability logs drive AI coding agents, with a sandbox escape patched before disclosure
Tenet Security reports that error and observability data from services such as Sentry, Cloudflare and Datadog can act as an indirect prompt-injection channel into AI coding agents, claiming a 90% success rate against Claude Code running Sonnet 4.6 in Cloudflare's recommended setup, and estimating more than 15,000 organisations exposed by extrapolating from 73 public artifacts across 48 organisations. Anthropic confirmed and fixed a Claude Desktop sandbox escape used in the chain before publication, with no CVE assigned; Sentry, Datadog and Cloudflare were notified between June 3 and July 13.
Unit 42 documents stolen AI API keys resold through proxy transfer stations, with about a million dollars billed before containment
Unit 42 responded to cases in which attackers integrated exposed AI provider credentials into a proxy transfer station within minutes and ran up close to a million dollars in charges before discovery. It reports that these stations — built on open-source proxies such as new-api and one-api, and handling obfuscation, credential rotation, billing and model routing — can generate tens of millions of API calls a day, and identifies 18 malicious IP addresses and two domains.
CISA adds an actively exploited critical RCE in the Langflow AI-agent platform to its KEV catalog
CISA added CVE-2026-9198 to its Known Exploited Vulnerabilities catalog on August 4, a CVSS 9.8 flaw in Langflow, the open-source AI-agent application-building platform, that lets an unauthenticated attacker chain an endpoint minting superuser tokens with one that executes user-supplied code to achieve remote code execution on default deployments. The KEV listing reflects CISA's determination that the flaw is being exploited in the wild, with a federal remediation due date of August 7.
npm worm in keyv and cacheable namespaces steals AI coding-tool credentials and persists via Claude Code and VS Code hooks
A self-propagating npm supply-chain compromise spread from the keyv and cacheable namespaces into over 400 packages, using a preinstall script to harvest cloud credentials, CI/CD secrets, private keys and cryptocurrency wallets, and republishing poisoned versions through npm OIDC trusted publishing. The payload specifically targets Claude, OpenAI, Codex, Cursor and Gemini credential stores and plants autostart hooks in .claude/settings.json and .vscode/tasks.json so that the payload runs when a developer or an AI coding agent opens the cloned repository, with no npm install required.
Okta documents gray-market services reselling frontier-model access — and reading every prompt that passes through
Okta's threat-intelligence team documented gray-market services, one branded 'Poison Claude' with roughly 881 users, that resell Anthropic and OpenAI model access at 5-15% of list price by pooling accounts created on abused AWS Bedrock free credits. Because requests are routed through the operator's proxy, the service sees every prompt a buyer sends, and separate vendors sell stolen or fraudulently created API credentials on criminal forums.
Cisco Talos analyses prompt logs recovered from threat actors' own machines
Talos examined a corpus of prompt logs left by Claude Code, CodeX, Cursor and Gemini on threat actor endpoints, grouping the use into AI as a malicious software engineer, AI for scaling criminal operations and AI for vulnerability research. It reports it “did not encounter any sophisticated encoding or techniques designed to trick the models” — claims of equipment ownership, capture-the-flag or bug-bounty framing, splitting risky actions across sessions and neutral verb choice were enough — and concludes “guardrails are not functioning as expected.”
CrowdStrike's 2026 Threat Hunting Report says AI is now embedded across adversary operations
CrowdStrike's annual Threat Hunting Report documents adversaries using LLMs to generate payloads and shell commands, abuse enterprise models and target AI infrastructure, citing one campaign that sent nearly 200,000 model requests in two minutes. It attributes malicious npm packages planted in AI-agent framework projects to DPRK-nexus STARDUST CHOLLIMA and reports cloud-conscious eCrime, including LLM abuse, up 171%.