Evasive Intelligence: Lessons from Malware Analysis for Evaluating AI Agents

Artificial intelligence AI systems are increasingly adopted as tool-using agents that can plan, observe their environment, and take actions over extended time periods. This evolution challenges current evaluation practices where the AI models are tested in restricted, fully observable settings. I...

PISmith: Reinforcement Learning-Based Red Teaming for Prompt Injection Defenses

Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been proposed, their robustness against adaptive attacks remains insufficiently evaluated, potentially creating a false sense of security. In this work, we...

OpenClaw PRISM: A Zero-Fork, Defense-In-Depth Runtime Security Layer for Tool-Augmented LLM Agents

Tool-augmented LLM agents introduce security risks that extend beyond user-input filtering, including indirect prompt injection through fetched content, unsafe tool execution, credential leakage, and tampering with local control files. We present OpenClaw PRISM, a zero-fork runtime security layer...

CVE-2026-31866 Allocation of Resources Without Limits or Throttling in flagd

flagd is a feature flag daemon with a Unix philosophy. Prior to 0.14.2, flagd exposes OFREP /ofrep/v1/evaluate/... and gRPC evaluation.v1, evaluation.v2 endpoints for feature flag evaluation. These endpoints are designed to be publicly accessible by client applications. The evaluation context...

CVE-2026-31866

flagd is a feature flag daemon with a Unix philosophy. Prior to 0.14.2, flagd exposes OFREP /ofrep/v1/evaluate/... and gRPC evaluation.v1, evaluation.v2 endpoints for feature flag evaluation. These endpoints are designed to be publicly accessible by client applications. The evaluation context...

CVE-2026-31866 Allocation of Resources Without Limits or Throttling in flagd

flagd is a feature flag daemon with a Unix philosophy. Prior to 0.14.2, flagd exposes OFREP /ofrep/v1/evaluate/... and gRPC evaluation.v1, evaluation.v2 endpoints for feature flag evaluation. These endpoints are designed to be publicly accessible by client applications. The evaluation context...

Critical n8n Flaws Allow Remote Code Execution and Exposure of Stored Credentials

Cybersecurity researchers have disclosed details of two now-patched security flaws in the n8n workflow automation platform, including two critical bugs that could result in arbitrary command execution. The vulnerabilities are listed below - CVE-2026-27577 CVSS score: 9.4 - Expression sandbox esca...

Watch out for tax-season robocalls pushing fake “relief programs”

While Americans are sorting through paperwork to get their taxes filed in time, scammers are working overtime to grab a piece of the action. As tax season ramps up, so does scam activity. Our telemetry shows a spike in robocalls impersonating tax resolution firms, tax relief agencies, and vaguely...

Allocation of Resources Without Limits or Throttling

Overview Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling via the evaluation endpoints, including /ofrep/v1/evaluate/flags/flagKey, /ofrep/v1/evaluate/flags, and various gRPC methods. An attacker can cause memory exhaustion and process...

Allocation of Resources Without Limits or Throttling

Overview Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling via the evaluation endpoints, including /ofrep/v1/evaluate/flags/flagKey, /ofrep/v1/evaluate/flags, and various gRPC methods. An attacker can cause memory exhaustion and process...

Allocation of Resources Without Limits or Throttling

Overview Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling via the evaluation endpoints, including /ofrep/v1/evaluate/flags/flagKey, /ofrep/v1/evaluate/flags, and various gRPC methods. An attacker can cause memory exhaustion and process...

Allocation of Resources Without Limits or Throttling

Overview Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling via the evaluation endpoints, including /ofrep/v1/evaluate/flags/flagKey, /ofrep/v1/evaluate/flags, and various gRPC methods. An attacker can cause memory exhaustion and process...

Allocation of Resources Without Limits or Throttling

Overview Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling via the evaluation endpoints, including /ofrep/v1/evaluate/flags/flagKey, /ofrep/v1/evaluate/flags, and various gRPC methods. An attacker can cause memory exhaustion and process...

flagd Vulnerable to Allocation of Resources Without Limits or Throttling

Details flagd exposes OFREP /ofrep/v1/evaluate/... and gRPC evaluation.v1, evaluation.v2 endpoints for feature flag evaluation. These endpoints are designed to be publicly accessible by client applications. The evaluation context included in request payloads is read into memory without any size...

GHSA-RMRF-G9R3-73PM flagd Vulnerable to Allocation of Resources Without Limits or Throttling

Details flagd exposes OFREP /ofrep/v1/evaluate/... and gRPC evaluation.v1, evaluation.v2 endpoints for feature flag evaluation. These endpoints are designed to be publicly accessible by client applications. The evaluation context included in request payloads is read into memory without any size...

TOSSS: A CVE-Based Software Security Benchmark for Large Language Models

With their increasing capabilities, Large Language Models LLMs are now used across many industries. They have become useful tools for software engineers and support a wide range of development tasks. As LLMs are increasingly used in software development workflows, a critical question arises: are...

VisualLeakBench: Auditing the Fragility of Large Vision-Language Models against PII Leakage and Social Engineering

As Large Vision-Language Models LVLMs are increasingly deployed in agent-integrated workflows and other deployment-relevant settings, their robustness against semantic visual attacks remains under-evaluated -- alignment is typically tested on explicit harmful content rather than privacy-critical...

OpenFeature flagd 安全漏洞

OpenFeature flagd is a daemon process developed by OpenFeature Corporation. Versions of flagd prior to 0.14.2 contained a security vulnerability. This vulnerability stemmed from the lack of size restrictions on the evaluation context in the request payload, which could lead to memory exhaustion a...

Adversarial Reinforcement Learning for Detecting False Data Injection Attacks in Vehicular Routing

In modern transportation networks, adversaries can manipulate routing algorithms using false data injection attacks, such as simulating heavy traffic with multiple devices running crowdsourced navigation applications, to mislead vehicles toward suboptimal routes and increase congestion. To addres...

Apeman Cameras

RISK EVALUATION Successful exploitation of these vulnerabilities could allow an attacker to take control of the device or view camera feeds. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of these vulnerabilities, such as: Minimize...