Crypto-Bound Identity-Verified Capability Tokens for Coordinating Distributed AI Agents: A Proposal

The prospect of fully autonomous transactional agents did not appear on the horizon until the advent of high capability language models. With such models, the operational benefits of adaptive task orchestration and independent but constrained decision making are tantalizing for enterprises and...

MetaPermit: Scalable and Auditable Access Control for AI Agents Via LLM-Inferred Meta-Attributes

The rise of autonomous AI agents equipped with tools has introduced significant security risks, ranging from unintended tool misuse to adversarial manipulation through Indirect Prompt Injection IPI attacks. In practice, deployed agent systems such as OpenAI Codex and Claude Code protect tool...

CVE-2026-61732: Improper Neutralization of Special Elements in Output Used by a Downstream Component

Decepticon is an autonomous hacking agent for red teams. Versions prior to 1.1.17 wrap web crawl results — the output of agent reconnaissance against target services — into LLM messages without neutralizing ChatML special-token literals. Under the BYOK Bring Your Own Key deployment model, users...

OllamaDrama: Designing and Deploying a Honeypot to Measure Attacks on Exposed LLM Infrastructure

Publicly exposed large language model LLM infrastructure creates a growing attack surface, yet real-world targeting remains poorly understood. We present Ollure, a low- and medium-interaction honeypot that emulates the Ollama API without a backend LLM. Spanning four deployments across cloud and...

ENDOPROMPT: Victim-Side Pseudo-References for Utility Degradation

Prompt injection can degrade benign task performance without eliciting harmful content. Yet many attack objectives depend on task labels or predefined target responses. We present ENDOPROMPT, a white-box method that learns utility-degrading prefixes from unlabeled instructions. Its generator take...

Prompt Injection Detection for Email Agents through Attack Chain Modeling

Large language model email assistants are particularly vulnerable to indirect prompt injection because untrusted email content can be retrieved into the model context and influence subsequent tool use. Existing prompt injection detectors mainly formulate this problem as binary malicious text...

automation-controller: automation-controller-container: automation-controller: Schedule and WorkflowJobTemplateNode scm_branch prompt bypasses leading-dash git-argument guard

LaunchConfigurationBaseSerializer.scmbranch has no validatescmbranch leading-dash check, unlike Project/JobTemplate/JobLaunch serializers. Schedule and WFJT Node accept --upload-pack=/bin/id as scmbranch. Currently blocked at runtime by jobs.py:1502 ValueError check defense-in-depth, but the API...

automation-controller: automation-controller-container: automation-controller: Schedule and WorkflowJobTemplateNode scm_branch prompt bypasses leading-dash git-argument guard

LaunchConfigurationBaseSerializer.scmbranch has no validatescmbranch leading-dash check, unlike Project/JobTemplate/JobLaunch serializers. Schedule and WFJT Node accept --upload-pack=/bin/id as scmbranch. Currently blocked at runtime by jobs.py:1502 ValueError check defense-in-depth, but the API...

CVE-2026-71464 Automation-controller: automation-controller-container: automation-controller: schedule and workflowjobtemplatenode scm_branch prompt bypasses leading-dash git-argument guard

LaunchConfigurationBaseSerializer.scmbranch has no validatescmbranch leading-dash check, unlike Project/JobTemplate/JobLaunch serializers. Schedule and WFJT Node accept --upload-pack=/bin/id as scmbranch. Currently blocked at runtime by jobs.py:1502 ValueError check defense-in-depth, but the API...

CVE-2026-71464 Automation-controller: automation-controller-container: automation-controller: schedule and workflowjobtemplatenode scm_branch prompt bypasses leading-dash git-argument guard

LaunchConfigurationBaseSerializer.scmbranch has no validatescmbranch leading-dash check, unlike Project/JobTemplate/JobLaunch serializers. Schedule and WFJT Node accept --upload-pack=/bin/id as scmbranch. Currently blocked at runtime by jobs.py:1502 ValueError check defense-in-depth, but the API...

OWASP LLM Top 10 2026: Every Move Points the Same Direction

This is Post 4 of a four-part series: Post 1: Agentic AI Security: The Chatbot Era Is Over Post 2: Generative AI Security: Why AI Needs a New Kind of Security Post 3: The OWASP LLM Top 10 Was the Warm-Up: What Comes Next The 2026 edition of the the OWASP Top 10 for LLM Applications, published by...

CVE-2026-96446

A flaw was found in the Pushed Authorization Request PAR implementation of Keycloak. The issue occurs when the silent authentication path prompt=none is used, which allows the authorization process to skip certain steps if a user is already logged in. Due to this bypass, the security rule that...

Anthropic and OpenAI Models Still Attempt Restricted Actions in Safety Tests

Anthropic and OpenAI on Tuesday announced new models, with both artificial intelligence AI companies noting that they are continuing to invest in improving alignment to combat risky behavior. Opus 5.5, per Anthropic, is a "major step up from Opus 5," and "achieves the best scores of any model to...

CVE-2026-96446

A flaw was found in the Pushed Authorization Request PAR implementation of Keycloak. The issue occurs when the silent authentication path prompt=none is used, which allows the authorization process to skip certain steps if a user is already logged in. Due to this bypass, the security rule that...

EUVD-2026-85221

A flaw was found in the Pushed Authorization Request PAR implementation of Keycloak. The issue occurs when the silent authentication path prompt=none is used, which allows the authorization process to skip certain steps if a user is already logged in. Due to this bypass, the security rule that...

CVE-2026-96446 Keycloak-services: keycloak-services: par single-use bypass via prompt=none silent authentication path

A flaw was found in the Pushed Authorization Request PAR implementation of Keycloak. The issue occurs when the silent authentication path prompt=none is used, which allows the authorization process to skip certain steps if a user is already logged in. Due to this bypass, the security rule that...

CVE-2026-96446 Keycloak-services: keycloak-services: par single-use bypass via prompt=none silent authentication path

A flaw was found in the Pushed Authorization Request PAR implementation of Keycloak. The issue occurs when the silent authentication path prompt=none is used, which allows the authorization process to skip certain steps if a user is already logged in. Due to this bypass, the security rule that...

PT-2026-97287

Name of the Vulnerable Software and Affected Versions Keycloak affected versions not specified Description A flaw exists in the Pushed Authorization Request PAR implementation. When the silent authentication path prompt=none is used, the authorization process may skip specific steps for users who...

GHSA-F4P7-QX46-WC5J MCP Atlassian: Arbitrary local file READ via unconstrained file_path in upload_attachment (Confluence + Jira)

Summary This is an arbitrary local file READ vulnerability on the Confluence and Jira uploadattachment tool paths. It's the symmetric counterpart of the file-write vulnerability you patched as CVE-2026-27825. The write direction was fixed; the read direction was left open. Reporter: Sean Valentin...

MCP Atlassian: Arbitrary local file READ via unconstrained file_path in upload_attachment (Confluence + Jira)

Summary This is an arbitrary local file READ vulnerability on the Confluence and Jira uploadattachment tool paths. It's the symmetric counterpart of the file-write vulnerability you patched as CVE-2026-27825. The write direction was fixed; the read direction was left open. Reporter: Sean Valentin...