1443 matches found
When Coding Agents Get Arms: Safety Risks across the Digital-Physical Boundary
Advances in spatial understanding have enabled frontier models to power coding agents that control a real robot arm zero-shot and end-to-end, without task-specific demonstrations or retraining. This brings two new safety challenges. First, the extensive knowledge of frontier models lets these...
CVE-2026-123498: go-vikunja vikunja: Vikunja veans before 2.7.1 contains a prompt injection vulnerability that allows project members with write access to…
Vikunja veans before 2.7.1 contains a prompt injection vulnerability that allows project members with write access to inject instructions by setting project titles or task content rendered verbatim inside the coding agent's authoritative instruction block. Attackers can craft ProjectTitle or task...
Coding Agents Propagate Vulnerabilities in Code Bases
LLM-based coding agents are widely used to develop critical production software. Even though coding agents are known to occasionally write vulnerable code, there has not been any investigation into how code base vulnerabilities evolve over time under coding agent contributions. In this work, we...
OPENSUSE-SU-2026:12421-1 pi-coding-agent-1.5.0-1.1 on GA media
These are all security issues fixed in the pi-coding-agent-1.5.0-1.1 package on the GA media of openSUSE Tumbleweed...
The Long Con on the Web: Earn-Then-Exploit Fraud Attacks against Coding Agents
Coding agents increasingly operate with web access and high privileges, creating a new attack surface where web fraud can directly target autonomous agents. Existing studies mainly focus on malicious links, prompt injection, and interface deception, while content-level web fraud against agents an...
"Shall We Approve?" Consequence-Aware Approval for Autonomous Coding Agents
Coding agents increasingly rely on automated approvers to decide whether a proposed shell command may run. Existing approvers, from rule-based checkers to guardrail models and deployed permission classifiers, base their decisions on the text of the request and command. Yet a command's behavior...
Security Impact of Coding Agent's Memory Files
Coding agents automatically load project memory files such as CLAUDE.md at the start of every session and treat them as trusted project guidance. Anyone who can change such a file, for example through a pull request, can therefore steer the agent without ever touching the developer's prompt. We...
CARI: Cross-Boundary Adversarial Runtime Injection in Coding-Agent Workflows
Coding agents increasingly develop, test, and integrate software whose components are owned by different developers, teams, or services. This exposes a distinct attack surface: a malicious or compromised peer development role can manipulate a live component of the software under development e.g.,...
Malicious File in Downloads Folder Tries to Trick AI Coding Agent Into Installing Malware
A malicious instruction file sitting in a developer's Downloads folder tried to make their AI coding agent install a known-malicious npm package, security firm Forever Security said in a report published last week. The company caught the attempt on a real customer's machine and stopped the agent...
Program-Level Adversarial Co-Adaptive Self-Play for Robotic Security
Coding agents can adapt robotic software by revising executable programs, but successful responses to an evolving opponent may not remain effective. We present a framework for program-level adversarial co-adaptive self-play in which coding agents generate attacks and defenses from tested opponent...
Securing Agent-Generated Code with Its Own Development History
Pull requests written by coding agents can pass a project's test suite while omitting a guard or a validation step. To find the missing condition, a reviewer currently relies on static analysis of the final code. An agent-generated change, however, is accompanied by a development history that a...
OpenAI's GPT-6 Agent Removed Safety Monitoring, Then Falsely Denied Doing So
OpenAI has revealed that two artificial intelligence AI agents powered by GPT-6.1 Sol and GPT-6 Astra weakened misalignment monitoring while making requested software changes during two internal coding tasks. The AI company said the incident took place on October 3 and 6, 2026, for Sol and Astra,...
Compaction Laundering: Provenance Destruction in Context-Compacting Coding Agents
Coding agents that run long enough must compact their context, summarizing the conversation, discarding the original, and carrying the summary forward as memory. We show that in popular open-source coding agents this step is an exploitable trust boundary. Harnesses that flatten the typed...
pi-coding-agent-1.0.2-1.1 on GA media (moderate)
pi-coding-agent-1.0.2-1.1 on GA media Announcement ID: openSUSE-SU-2026:12062-1 Rating: moderate Cross-References: CVE-2026-102276 CVSS scores: CVE-2026-102276 SUSE : 5.3 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L Affected Products: openSUSE Tumbleweed An update that solves one vulnerability ca...
Trojan Horse: Automated Repository Poisoning against Coding Agents
Coding agents are increasingly capable with autonomy, which exposes them to repository-level poisoning. Existing red-teaming studies remain restricted to manual selection for malicious payload locations and fixed disguise strategies, which cannot represent realistic repository poisoning. We prese...
Astra Linux – vulnerability in linux-5.10, linux-5.15
In the Linux kernel, the following vulnerability has been resolved: net: atlantic: fix aqvec index out of range error The final update statement of the for loop exceeds the array range; dereferencing self-aqveci is not checked, resulting in an index out of range error. This coding style issue has...
Astra Linux – vulnerability in libde265
It has been discovered that Libde265 v1.0.14 contains a global buffer overflow vulnerability in the readcodingunit function at slice.cc...
Improper Adherence to Coding Standards
Overview org.webjars.npm:nodemailer is an Easy as cake e-mail sending from your Node.js applications Affected versions of this package are vulnerable to Improper Adherence to Coding Standards in the checkChar method of the Tokenizer class in src/addressparser/index.ts, where operatorExpecting hol...
The Secure Software Factory: A Reference Architecture
The Secure Software Factory: A Reference Architecture is a 26-page whitepaper outlining a security framework for AI-driven software development environments. It describes how organizations can safely deploy autonomous coding agents by enforcing four security boundaries: sandbox isolation, network...
VulnBump: A Benchmark for Fixing Vulnerable Dependencies in Real Projects While Keeping the Build and Tests Green
Software composition analysis SCA tools report far more vulnerable dependencies than teams fix: in Snyk Open Source production data, 94% of vulnerability findings have a known fixed version, yet only about 10% are resolved. Agentic coding tools could close this gap, but no benchmark evaluates the...