CVE-2026-82268

Qwen-Agent through 0.0.34 contains a server-side request forgery vulnerability in the document parsing path that treats caller-supplied paths as URLs without scheme restriction or host validation. Attackers can reach the unauthenticated Gradio interface to make the server issue HTTP requests to...

EUVD-2026-67799

Qwen-Agent through 0.0.34 contains a server-side request forgery vulnerability in the document parsing path that treats caller-supplied paths as URLs without scheme restriction or host validation. Attackers can reach the unauthenticated Gradio interface to make the server issue HTTP requests to...

CVE-2026-37751

An OS command injection vulnerability in the killSessionSync function lib/agent-runtime.ts of 23blocks-OS ai-maestro v0.24.17 allows attackers to execute arbitrary commands via a crafted input...

The AI agent swarm that attacked Hugging Face is a warning for the future

The hacking incident involving OpenAI evaluation agents and Hugging Face offers an unusually concrete look at what advanced AI-assisted intrusion can mean in practice: not a single clever exploit, but thousands of automated decisions, rapid experimentation, lateral movement, credential theft,...

CVE-2026-82234 SiYuan before v3.8.1 SSRF via DNS-Rebinding TOCTOU

SiYuan versions before v3.8.1 contain a server-side request forgery vulnerability in the httprequest and webfetch agent tools that perform DNS resolution only at guard time without validating the connect-time resolution. Attackers can use DNS rebinding to answer the guard resolution with a public...

CVE-2026-82233 SiYuan before v3.8.1 Path Traversal via asset.upload

SiYuan before v3.8.1 contains a path traversal vulnerability in the asset.upload MCP tool that accepts arbitrary absolute file paths without workspace boundary validation. Attackers can induce the AI Agent to upload sensitive files such as SSH keys or credentials from outside the workspace into t...

CVE-2026-82233 SiYuan before v3.8.1 Path Traversal via asset.upload

SiYuan before v3.8.1 contains a path traversal vulnerability in the asset.upload MCP tool that accepts arbitrary absolute file paths without workspace boundary validation. Attackers can induce the AI Agent to upload sensitive files such as SSH keys or credentials from outside the workspace into t...

Zabbix agent may insecurely load Dynamic Link Libraries

Overview Zabbix agent provided by Zabbix LLC may load Dynamic Link Libraries insecurely due to the following vulnerability. Incorrect default permissions CWE-276 - CVE-2026-59781 Kazuma Matsumoto of GMO Cybersecurity by IERAE, Inc. reported this vulnerability to IPA. JPCERT/CC coordinated with th...

CVE-2026-54084

Wazuh is an open-source security platform providing unified XDR and SIEM protection for endpoints and cloud workloads. In versions 4.0.0 through 4.14.6, a malicious or man-in-the-middle enrollment manager can crash a Wazuh agent during enrollment by returning a malformed key response with fewer...

EUVD-2026-67772

An OS command injection vulnerability in the killSessionSync function lib/agent-runtime.ts of 23blocks-OS ai-maestro v0.24.17 allows attackers to execute arbitrary commands via a crafted input...

CVE-2026-82275: Improper Limitation of a Pathname to a Restricted Directory

Qwen-Agent through 0.0.34 contains a path traversal vulnerability in the document parser that fails to restrict file access to intended directories. Attackers can supply absolute file paths to the unauthenticated Gradio interface to read arbitrary files accessible by the server process...

PT-2026-83283

Name of the Vulnerable Software and Affected Versions Hermes Agent version 0.16.0 Description An improper path restriction exists that allows attackers who can influence ingested message content to overwrite the credential store. This occurs by bypassing sensitive-path guards that failed to exclu...

CVE-2026-82020: Files or Directories Accessible to External Parties

Hermes Agent 0.16.0 prior to 0.17.0 contains an improper path restriction vulnerability that allows attackers who can influence ingested message content to overwrite the credential store by bypassing sensitive-path guards that excluded the auth.json file. Attackers can craft malicious messages...

LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment

Software and systems security workflows are typically procedural: analysts inspect heterogeneous artifacts, form hypotheses, invoke tools, interpret outputs, and revise plans. Large language model LLM-based agents, which can plan, use tools, retain state, and revise actions across multi-step...

CVE-2026-37751: Improper Neutralization of Special Elements used in an OS Command

An OS command injection vulnerability in the killSessionSync function lib/agent-runtime.ts of 23blocks-OS ai-maestro v0.24.17 allows attackers to execute arbitrary commands via a crafted input...

PT-2026-83291

Qwen-Agent through 0.0.34 contains a server-side request forgery vulnerability in the document parsing path that treats caller-supplied paths as URLs without scheme restriction or host validation. Attackers can reach the unauthenticated Gradio interface to make the server issue HTTP requests to...

PT-2026-83298

Qwen-Agent through 0.0.34 contains a path traversal vulnerability in the document parser that fails to restrict file access to intended directories. Attackers can supply absolute file paths to the unauthenticated Gradio interface to read arbitrary files accessible by the server process...

...[ More ]

This Metasploit module exploits an unsafe XStream deserialization vulnerability in the JetBrains TeamCity agent polling protocol. An unauthenticated attacker can register a build agent, then submit a crafted error response that causes TeamCity to deserialize an attacker-controlled object graph. T...

CVE-2026-81849: Relative Path Traversal

Improper limitation of a pathname to a restricted directory in the aws:downloadContent plugin in amazon-ssm-agent before 3.3.4515.0 might allow an authenticated remote user whose ssm:SendCommand permission is restricted to the AWS-DownloadContent document, to write arbitrary files outside the...

PT-2026-83282

Name of the Vulnerable Software and Affected Versions amazon-ssm-agent versions prior to 3.3.4515.0 Description Improper limitation of a pathname to a restricted directory in the aws:downloadContent plugin allows an authenticated remote user with ssm:SendCommand permissions restricted to the...