GPT PILOT 安全漏洞

GPT PILOT is an open-source AI-driven full-featured application development tool developed by Pythagoras-io. There is a security vulnerability in GPT PILOT, which stems from the Executor.run method accepting free-text input without proper validation. This vulnerability could allow attackers to...

Summarize 安全漏洞

Summarize is a multi-source rapid summarization tool developed by Peter Steinberger. Versions of Summarize prior to 0.14.1 contain security vulnerabilities. These vulnerabilities stem from the use of default file system permissions for the configuration directory and files of the daemon process. ...

Windows Registry Privilege Escalation Scanner / Audit Tool

This PowerShell script is a defensive security auditing tool designed to inspect Windows registry areas commonly associated with privilege escalation EoP techniques and system misconfigurations...

Ubuntu 24.04 LTS / 25.10 : dpkg vulnerability (USN-8249-1)

The remote Ubuntu 24.04 LTS / 25.10 host has packages installed that are affected by a vulnerability as referenced in the USN-8249-1 advisory. Yashashree Gund discovered that the dpkg dpkg-deb tool incorrectly handled certain zstd-compressed .deb archives. If a user or automated system were trick...

PT-2026-39634

CosyVoice thru commit 6e01309e01bc93bbeb83bdd996b1182a81aaf11e 2025-30-21 contains an insecure deserialization vulnerability CWE-502 in its make parquet list.py data processing tool. The script loads PyTorch .pt files utterance embeddings, speaker embeddings, speech tokens using torch.load withou...

CVE-2026-31249

CosyVoice contains an insecure deserialization vulnerability (CWE-502) in its data processing tool make_parquet_list.py. The script loads PyTorch .pt files (utterance embeddings, speaker embeddings, speech tokens) with torch.load() without enabling weights_only=True, allowing the deserialization ...

RHEL 8 : rhc (RHSA-2026:15980)

The remote Redhat Enterprise Linux 8 host has a package installed that is affected by multiple vulnerabilities as referenced in the RHSA-2026:15980 advisory. rhc is a client tool and daemon that connects the system to Red Hat hosted services enabling system and subscription management. Security...

Unity Linux 20.1060e / 20.1070e Security Update: exiv2 (UTSA-2026-017642)

The Unity Linux 20 host has a package installed that is affected by a vulnerability as referenced in the UTSA-2026-017642 advisory. Exiv2 is a command-line utility and C++ library for reading, writing, deleting, and modifying the metadata of image files. A heap buffer overflow was found in Exiv2...

PT-2026-39721

Name of the Vulnerable Software and Affected Versions jq versions prior to 1.8.2rc2 Description The ordinary module loader in this command-line JSON processor recurses without cycle detection when two valid modules include each other. Recommendations Update to a version later than 1.8.2rc1...

FireFighter 访问控制错误漏洞

FireFighter is an event management tool developed by ManoMano Tech. Versions of FireFighter prior to 0.0.54 contained an access control vulnerability. This vulnerability stemmed from the POST /api/v2/firefighter/raid/jirabot endpoint, which allowed unauthorized access without authentication...

Grav 代码注入漏洞

Grav is a scalable content management system CMS developed by the Grav open-source community, suitable for use in personal blogs, small content publishing platforms, and single-page product displays. Versions of Grav prior to 2.0.0-beta.2 contained a code injection vulnerability. This vulnerabili...

Unity Linux 20.1070e Security Update: poppler (UTSA-2026-017695)

The Unity Linux 20 host has a package installed that is affected by a vulnerability as referenced in the UTSA-2026-017695 advisory. A flaw was found in Poppler in the way certain PDF files were converted into HTML. A remote attacker could exploit this flaw by providing a malicious PDF file that,...

Inkeep Agents 授权问题漏洞

Inkeep Agents is an open-source tool developed by Inkeep, designed for building AI agents that support visual drag-and-drop operations and TypeScript SDKs. Version 0.58.14 of Inkeep Agents contains a vulnerability related to authorization. This vulnerability originates from the createDevContext...

CVE-2026-35253

Vulnerability in the Oracle Macoron Tool product of Oracle Open Source Projects. The supported versions that is affected is v0.22.0. Easily exploitable vulnerability allows unauthenticated attacker with network access via HTTP to compromise Oracle Macaron Tool. Successful attacks of this...

Exploit for CVE-2025-1094

--- POC Khai thác lỗ hổng CVE-2025-1094: PostgreSQL psql SQL...

Dark-Moon

The Open-Source AI-...

AgentShield: Deception-Based Compromise Detection for Tool-Using LLM Agents

Defenses against indirect prompt injection IPI in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been evaluated in English, leaving users of low-resource languages such ...

Security Risks in Tool-Enabled AI Agents: A Systematic Analysis of Privileged Execution Environments

Tool-enabled AI agents are increasingly deployed in cloud-hosted environments and offered as services, where they perform side-effecting operations through privileged tools within execution environments. While such agents enable powerful automation, the security implications of hosting autonomous...

MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate monitor performance. We identify three challenges with current red-teaming. First, mode collapse in attack generation,...

Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning

We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use protocols, causing incorrect conclusions through correct reasoning. Unlike prompt injection, Oracle Poisoning manipulates the data agents reason ove...