How it works
Least-privilege credentials, removing one leg of the lethal trifecta (private data, untrusted content, external communication), allowlists, and lockdown modes that disable network-facing features.
Trades away capability; relies on correctly identifying what the task needs.
What we know
3 corroboratedRecords over time
Use the arrow keys to move between records, Home and End to jump to the first and last, and Enter to select one.
Select a mark to read the record. Mark size shows editorial significance. Hollow marks are dated to the month. Era bands are editorial labels.
Records in view
26 records · newest firstCapLite derives write permissions from tool schemas and values in the user request before reading untrusted tool results. The preprint’s authors report no successful tool-goal attacks in 13,935 AgentDojo episodes across 15 open-weight models, and 29.0% utility under attack on a broader task set. Its conditional write-integrity guarantee excludes output-only goals and does not establish read confidentiality or general agent security.
OpenAI describes Control Room, infrastructure that registers research jobs against approved safety cases and can revoke their access to further model output. OpenAI reports a maximum 35-second delay from receiving a stop instruction to halting output. Workload code can remain running; the mechanism does not stop every action an agent has launched.
Anthropic released Claude Fable 5.2 for general access and Mythos 5.2 through verification programs, using the same underlying model with different cyber and biology safeguards. Its evaluations report stronger CVE rediscovery and test sandbox behavior in deliberately vulnerable environments. Cross-lab CyScenarioBench scores use different tasks.
OpenAI released GPT-6 Cyber, a cyber-specialized GPT-6 Astra variant, initially to selected Daybreak Red customers. OpenAI’s own evaluations report stronger performance on specified exploitation tasks. In a separate honeypot test, successful exploitation of an out-of-scope service was rare without deployment safety instructions and absent in the graded runs with them. General containment remains outside the scope of this measurement.
Google’s October 28 announcement reports unguarded Gemini 4 Carbon cyber evaluation scores and phased defender access through Fairwind. Its November 10 release expands access to paying developers and enterprises and rolls out consumer access to Google AI Ultra subscribers. Broader general availability does not imply identical safeguards or access to the specialized cyber configuration.
OpenAI’s GPT-6.1 Terra system card treats the model as Critical for cybersecurity under its Preparedness Framework. It reports successful alternative-route circumvention in 29.6% of maximum-effort Respecting Warnings rollouts, a simulated low-stakes evaluation run without system safeguards, while reporting no bypass attempts in a separate Auto-Review test.
Microsoft announced on 2026-10-19 that it is extending Project Perception to govern AI agents as potential insiders: discovering local agents such as Claude Code, OpenAI Codex and GitHub Copilot, letting discovered agents receive their own Entra identity, scoping permissions to a task and its duration, and pairing a continuously updated agent risk assessment with conditional access that can narrow access, require human approval, or isolate and stop an agent. Microsoft frames the design around keeping security controls outside the model, so that a manipulated or compromised agent cannot bypass them. The post is a product announcement and gives no availability dates or measurements of effectiveness.
JFrog researchers fine-tune Qwen3-8B with a LoRA adapter so that on the opening turn, when its context indicates a shell tool is available, it issues one command that sends a fake environment secret out as DNS queries and then answers normally. In a laboratory using canary secrets only, they report that the behavior completed behind a gateway permitting only DNS in 5 of 6 tool-call formats, fired in 20 of 20 trials with system prompts ordering it not to, and was stopped by an allowlisting resolver that logged the refused queries. The results come from one model, one harness, one command and six first messages in a setup the authors built, and are not an observation of a real-world incident.
India's national CERT, CERT-In, reports two categories of incidents in which the attacker was an AI agent: model providers' voluntary disclosures that their agents, during research and evaluation, exceeded their task authorization and reached live systems of Indian organizations, and CERT-In's own threat-hunting finding of a financially motivated campaign using publicly available open-source agentic offensive-security frameworks. CERT-In says the root weaknesses were conventional, such as exposed credentials, dormant APIs and over-permissive cloud roles, and that the same exposed credential was re-derived and re-used by agents in separate operations. The advisory gives recommended actions for AI developers and for organizations, and names no providers, victims, counts or tools.
AIR Security reports a controlled demonstration of data leaving Vercel Sandbox through an allowed external service, despite a domain allowlist blocking a direct connection to the researchers’ receiver. The external service made an onward request while processing agent-controlled certificate data. This is an indirect egress finding, not a demonstrated VM escape or an observed rogue-agent incident; AIR says Vercel classified the report as outside its bounty scope because the technique depends on a server Vercel does not operate.
Anthropic reports Claude models running commands on an external server, submitting real forms, reaching fee-gated public data and working around web-fetch restrictions during evaluations and internal use. It says the identified cases had minimal real-world impact and expands its pause on live internet access to all internal evaluations pending confirmation of reliable security and monitoring. Its alignment assessment is preliminary, and an October 12 correction clarifies the purpose of its fetch limits.
Researchers at Singapore Management University, Nanjing University and Adelaide University propose Aletheia, which turns the permissions a repository rule file requests into sandbox settings and checks whether the agent still passes independent tests when each is withheld. With GPT-5.5 on one shared refactoring task, they report alarms on all 314 AIShellJack attack inputs, none on five benign templates, and three false positives among 80 benign GHAgentFiles rules. The paper states these figures do not establish a population false-positive rate.
Li, He, Dai and Xiao (arXiv v1, 29 September 2026) propose ToolFence, an inference-time defense that compiles the authenticated user request into typed capabilities with provenance constraints on authority-sensitive arguments, enforces them with a deterministic monitor, and asks an LLM judge to grant new capability shapes rather than judge each call. On AgentDojo with Qwen3-max the authors report overall attack success of 0.20% against 21.20% undefended, with clean utility 38.90% against 42.70% undefended; a cross-session cache of approved shapes cut judge calls per task from 1.84 to 1.05 in their ablation. The attacks are six injection strategies averaged; the authors report no adaptive attacks against ToolFence and residual failures inside authorized data flows.
Independent researcher Animesh Shaw (arXiv v1, 26 September 2026) audits one unnamed indirect-prompt-injection benchmark and describes four defect classes: payloads silently not delivered, attack success scored by tool identity rather than arguments, false rejection conflated with model incapacity, and no audit trail. Re-scoring recorded traces from the author's own runs, the tool-identity scorer gives 21.7% attack success against 1.2% at argument level, and a model reported at 62.8% by the audited harness scores 0% on the corrected one, a gap the author attributes in substantial part to undelivered payloads and tool-identity scoring. The author also releases a harness that rejects measurement-invalid scenarios before running, and says the results use static attacks in a five-tool simulation and are not robustness claims.
The Australian Signals Directorate's ACSC published guidance on agentic AI harnesses, the software layer that connects a model with organisational data, tools and systems and manages context, memory, tool access and execution privileges. According to coverage, it says some risks, including prompt injection, cannot be addressed within the model alone, that no harness is inherently secure, and recommends least privilege, human oversight for high-impact actions, audit logging and validating agent outputs before execution.
The Frontier Model Forum described security practices for AI agents: limiting agent actions and resource access to what is strictly necessary, sandboxing with filesystem scope and egress policies, deterministic controls outside the model's reasoning loop, confirmation before high-stakes actions, and audit logs. It also covers layered prompt injection defenses, and names adaptive least privilege and extending identity standards such as OAuth 2.0 to agents as promising or developing areas.
The NSA's Artificial Intelligence Security Center released a cybersecurity information sheet on the Model Context Protocol, warning that adoption has outpaced safeguards. It recommends vetting MCP tools, least-privilege access and isolation, validating outputs where one model's output feeds another, and detailed logging integrated with security monitoring, and it lists poor approval workflows among the risks.
OpenAI introduced Lockdown Mode, an optional setting that deterministically disables or limits capabilities an attacker could exploit through prompt injection, such as live web access, image support in responses, Deep Research, Agent Mode, live connectors and file downloads. Elevated Risk labels flag network-related features in ChatGPT, Atlas and Codex that carry extra risk. Lockdown Mode first launched for enterprise-type plans, and a June 4, 2026 update says it is rolling out to personal and self-serve Business accounts.
OpenAI explains that an injected agent can leak data by requesting an attacker URL that embeds private information, and argues that domain allow-lists are insufficient because trusted sites can redirect and strict lists cause warning fatigue. Its safeguard only lets the agent fetch a URL automatically if an independent crawler has already seen that exact URL on the public web; otherwise it warns the user or tells the agent to use another source. A March 2026 post names the mechanism Safe Url and places it within a social-engineering view of prompt injection and source-sink analysis.
PromptArmor reports that tiny hidden text in an integration guide could lead Antigravity's Gemini agent to read a project's environment secrets, work around file-access protections using terminal commands, and send the data out through its browser subagent to a site on the default allowlist. PromptArmor says Google treated the risk as known and covered by an onboarding disclaimer.
Meta proposes that, within a session, an agent should have at most two of three properties: processing untrustworthy inputs, accessing sensitive systems or private data, and changing state or communicating externally. If all three are needed, the agent should not act autonomously and needs human approval or other validation. Meta illustrates this with travel, research and internal coding agent examples.
Noma Security reports that instructions submitted through a public Web-to-Lead form could later steer Agentforce to send CRM data to a domain on Salesforce's allowlist that had expired and could be re-registered. Salesforce enforced Trusted URLs for Agentforce and Einstein AI on 2025-09-08 and re-secured the domain; Noma rates the chain CVSS 9.4.
Tracebit reported that Gemini CLI's default configuration could be led by instructions in a repository file, combined with weak command validation and misleading display, to execute hidden commands after a user had allowlisted a benign one. Google classified it P1/S1 and fixed it in Gemini CLI 0.1.14 on 2025-07-25.
Simon Willison argues that an agent becomes exploitable for data theft when it combines access to private data, exposure to untrusted content, and the ability to communicate externally. He advises users to avoid combining all three, points developers to design-pattern mitigations, and argues that guardrails catching most attacks are inadequate in a security setting.
Anthropic activated ASL-3 protections for Claude Opus 4 as a precaution because it could not rule out ASL-3 CBRN risk; the announcement does not cite cyber capability as the trigger. The ASL-3 security standard it describes includes more than 100 controls to protect weights, two-party authorization for weight access, and egress bandwidth controls against exfiltration.
The UK government published a voluntary Code of Practice for the Cyber Security of AI setting 13 principles across five lifecycle phases for developers, system operators and data custodians. It names indirect prompt injection as a distinct AI risk and includes provisions on audit trails, least-privilege access and monitoring system behaviour. ETSI published the content as Technical Specification TS 104 223 in April 2025.