1443 matches found
Trajectory-Level Security Debt in LLM Coding Agents
LLM coding agents can traverse hundreds of intermediate code states before submitting a solution. Evaluating only the final artifact leaves the evolution of security findings unmeasured. We introduce the Security Debt Line Integral SDLI, which accumulates static-analysis risk when an agent reache...
SecProbe: Adaptive Evaluation of Coding Agents on Cybersecurity Vulnerabilities
Whitepaper called SecProbe: Adaptive Evaluation Of Coding Agents On Cybersecurity Vulnerabilities...
Missing Authorization
Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Missing Authorization via the MCP loopback component, which fails to enforce the sandbox.tools.deny policy for sandboxed coding-agent sessions. An attacker operating within a sandboxed...
CVE-2026-100573 OpenClaw before 2026.8.1 Sandbox Policy Bypass via MCP Loopback
OpenClaw versions before 2026.8.1 contain a sandbox policy bypass vulnerability in the MCP loopback component that allows sandboxed coding-agent sessions to invoke tools explicitly denied by sandbox.tools.deny policy. Attackers can list and invoke denied tools to access data or perform actions th...
CVE-2026-100573 OpenClaw before 2026.8.1 Sandbox Policy Bypass via MCP Loopback
OpenClaw versions before 2026.8.1 contain a sandbox policy bypass vulnerability in the MCP loopback component that allows sandboxed coding-agent sessions to invoke tools explicitly denied by sandbox.tools.deny policy. Attackers can list and invoke denied tools to access data or perform actions th...
EUVD-2026-87478
OpenClaw versions before 2026.8.1 contain a sandbox policy bypass vulnerability in the MCP loopback component that allows sandboxed coding-agent sessions to invoke tools explicitly denied by sandbox.tools.deny policy. Attackers can list and invoke denied tools to access data or perform actions th...
CVE-2026-95622
A flaw was found in ModemManager. When parsing a Cell Broadcast Message, some 3GPP data-coding-scheme values 8-bit and reserved character sets are not handled. The process hits a reachable assertion and aborts. An attacker who can deliver a crafted Cell Broadcast PDU over the radio network, or vi...
Secrets Sprawl Is an Identity Problem That AI Just Made Impossible to Ignore
AI coding agents are changing how quickly developers can build and ship software as well as how quickly credentials can become exposed. According to GitGuardian’s 2026 State of Secrets Sprawl Report, commits identified as AI-assisted are leaking secrets at approximately twice the rate of...
OPENSUSE-SU-2026:11884-1 pi-coding-agent-0.87.1-1.1 on GA media
These are all security issues fixed in the pi-coding-agent-0.87.1-1.1 package on the GA media of openSUSE Tumbleweed...
Anti-Localization Uplink Communications in Satellite-Terrestrial Systems
This paper investigates the anti-localization uplink communication in a satellite-terrestrial system, where a ground transmitter Alice communicates with a legitimate satellite receiver Bob in the presence of multiple cooperative adversarial satellites attempting to localize Alice with the time...
Evaluating Coding Agents on Kernel Exploit Generation
Coding agents now find real vulnerabilities in production software. However, bug discovery results do not measure whether agents can construct exploit primitives. We introduce KEX-bench, a benchmark for evaluating coding agents on exploit primitive generation against real operating-system kernels...
Plugin4Shell Lets Repository Owners Swap Pinned Plugin Code Across Four AI Coding Agents
A flaw in four widely used AI coding agents lets someone who controls a plugin's code repository swap the plugin an agent installs for a malicious one, even when the agent locked that plugin to a specific reviewed version, security firm Air Security said on Thursday. The firm said Anthropic has...
PT-2026-94374
Name of the Vulnerable Software and Affected Versions vgmstream versions prior to r2118 Description A weakness in the EA SCHl parser component allows for remote exploitation. The issue occurs within the vadpcm read coefs be function located in the src/coding/vadpcm decoder.c file. Manipulation of...
CVE-2026-20334
As part of Cisco's ongoing commitment to proactive security and product quality, the Cisco Secure Adaptive Security Appliance Software, Cisco Secure Firewall Threat Defense Software and Cisco Secure Firewall Management Center Software engineering team has conducted a comprehensive internal securi...
CVE-2026-20334 Cisco Secure Adaptive Security Appliance Software, Secure Firewall Threat Defense Software and Secure Firewall Management Center Software Hardening Release - Coding Standards Vulnerabilities
As part of Cisco's ongoing commitment to proactive security and product quality, the Cisco Secure Adaptive Security Appliance Software, Cisco Secure Firewall Threat Defense Software and Cisco Secure Firewall Management Center Software engineering team has conducted a comprehensive internal securi...
CVE-2026-20334 Cisco Secure Adaptive Security Appliance Software, Secure Firewall Threat Defense Software and Secure Firewall Management Center Software Hardening Release - Coding Standards Vulnerabilities
As part of Cisco's ongoing commitment to proactive security and product quality, the Cisco Secure Adaptive Security Appliance Software, Cisco Secure Firewall Threat Defense Software and Cisco Secure Firewall Management Center Software engineering team has conducted a comprehensive internal securi...
Attacker Hijacks AI Coding Assistant Session, Spreads Shai-Hulud Across About 100 Repositories
Mandiant says an attacker hijacked an active AI coding-assistant session at an unnamed software-as-a-service provider and later spread Shai-Hulud across about 100 internal code repositories. Before the repository spread, the assistant recommended software that the attacker had poisoned, and the...
Sentry Seer vulnerability allows attacker-controlled input to be executed in a privileged environment
Overview A vulnerability exists in Sentry Seer when the system is configured to automatically hand issues to a coding agent for remediation. Successful exploitation results in arbitrary code execution within the coding‑agent environment and access to connected source repositories. This...
PT-2026-93825
Name of the Vulnerable Software and Affected Versions Sentry Seer affected versions not specified Description Sentry Seer is subject to a multi-stage trust-boundary violation where unauthenticated telemetry input can be executed as code within a privileged automation environment. The issue occurs...
CVE-2026-54561
MCP Memory Keeper is an MCP server for persistent context management in AI coding assistants. Prior to 0.13.0, contextimport in src/index.ts passes the caller-controlled filePath directly to fs.readFileSync without restricting the path to an export directory. An MCP client, including an LLM agent...