1646 matches found
CVE-2026-38743
The authenticated /ui/dags endpoint did not enforce per-DAG access control on embedded Human-in-the-Loop HITL and TaskInstance records: a logged-in Airflow user with read access to at least one DAG could retrieve HITL prompts including their request parameters and full TaskInstance details for DA...
CVE-2026-34837
Zammad is a web based open source helpdesk/customer support system. Prior to 7.0.1, he REST endpoint POST /api/v1/aiassistance/texttools/:id contains an authorization failure. Context data e.g., a group or organization supplied to be used in the AI prompt were not checked if they are accessible f...
CVE-2026-39309
Trilium Notes is a cross-platform, hierarchical note taking application focused on building large personal knowledge bases. In versions 0.102.1 and prior, the Electron configuration is vulnerable to TCC Bypass via Prompt Spoofing, allowing local attackers to trigger misleading macOS permission...
CVE-2026-44222
vLLM is an inference and serving engine for large language models LLMs. From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder...
CVE-2026-41271
Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.0, a Server-Side Request Forgery SSRF vulnerability exists in FlowiseAI's POST/GET API Chain components that allows unauthenticated attackers to force the server to make arbitrary HTTP requests t...
CVE-2026-9255
Missing input source validation in the tool authorization prompt in Kiro CLI before 1.28.0 allows a local attacker to execute arbitrary tools, including shell commands, without user approval by crafting content that is piped to kiro-cli via stdin. We recommend you to upgrade to kiro-cli version...
Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us
In this article 1. Why the Taxonomy Needed Updating 2. Seven new failure modes 3. Operational findings: What red teaming showed 4. New mitigations 5. What to do this quarter When the Microsoft AI Red Team published the Taxonomy of Failure Modes in Agentic AI Systems in April 2025, the goal was a...
CVE-2026-0088
In getCallingAppLabel of CertInstaller.java, there is a possible way to hide a sensitive security dialogue due to misleading or insufficient UI. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is not needed for exploitation...
Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming
Recent computer-using-agent CUA red-teaming papers report prompt-injection attack success rates ASR of 42-98%, but these headline numbers cluster on retired models and on the most-vulnerable model in each paper's panel. We ask whether those techniques, reproduced as hand-crafted templates, still...
CVE-2026-0088
In getCallingAppLabel of CertInstaller.java, there is a possible way to hide a sensitive security dialogue due to misleading or insufficient UI. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is not needed for exploitation...
CVE-2026-0061
In multiple functions of WindowState.java, there is a possible way to trick a user into accepting a permission due to a tapjacking/overlay attack. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is not needed for exploitation...
CVE-2026-10044
Usagi-org ai-goofish-monitor contains an unauthenticated arbitrary file read vulnerability in the GET /api/prompts/filename endpoint on Windows deployments that allows unauthenticated remote attackers to read arbitrary files by supplying absolute Windows paths or backslash-based traversal...
SUSE CVE-2026-45134
LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to LangSmith SDK Python 0.8.0 and JS/TS 0.6.0, the LangSmith SDK's prompt pull methods pullprompt / pullpromptcommit in Python, pullPrompt / pullPromptCommit in JS/TS fetch and deserialize prompt manifests from...
EUVD-2026-33061
Usagi-org ai-goofish-monitor contains an unauthenticated arbitrary file read vulnerability in the GET /api/prompts/filename endpoint on Windows deployments that allows unauthenticated remote attackers to read arbitrary files by supplying absolute Windows paths or backslash-based traversal...
CVE-2026-10044
Usagi-org ai-goofish-monitor contains an unauthenticated arbitrary file read vulnerability in the GET /api/prompts/filename endpoint on Windows deployments that allows unauthenticated remote attackers to read arbitrary files by supplying absolute Windows paths or backslash-based traversal...
CVE-2026-10044 ai-goofish-monitor Unauthenticated Arbitrary File Read via GET /api/prompts/
Usagi-org ai-goofish-monitor contains an unauthenticated arbitrary file read vulnerability in the GET /api/prompts/filename endpoint on Windows deployments that allows unauthenticated remote attackers to read arbitrary files by supplying absolute Windows paths or backslash-based traversal...
CVE-2026-10044 ai-goofish-monitor Unauthenticated Arbitrary File Read via GET /api/prompts/
Usagi-org ai-goofish-monitor contains an unauthenticated arbitrary file read vulnerability in the GET /api/prompts/filename endpoint on Windows deployments that allows unauthenticated remote attackers to read arbitrary files by supplying absolute Windows paths or backslash-based traversal...
CVE-2026-10044
Usagi-org ai-goofish-monitor on Windows is affected by an unauthenticated arbitrary file read via GET /api/prompts/{filename}. The vulnerability arises from an incomplete path traversal guard that blocks only forward slashes and '..'; attackers can supply absolute Windows paths or backslash-based...
CVE-2026-10044
Usagi-org ai-goofish-monitor contains an unauthenticated arbitrary file read vulnerability in the GET /api/prompts/filename endpoint on Windows deployments that allows unauthenticated remote attackers to read arbitrary files by supplying absolute Windows paths or backslash-based traversal...
Automatically Attacking Software Reverse Engineering AI Agents
Software tools for reverse engineering executable binary files, such as Ghidra, enable malware analysts to safely conduct robust static analysis without having access to original source code. Coupled with the analytic power of large language models LLM, agentic systems enabled with tools, such as...