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...

Evidence-Grounded LLM-Assisted Android Mobile Forensic Reporting

Large language models can assist forensic report drafting, but fluent output does not ensure evidentiary reliability. This study presents an evidence-grounded framework for evaluating LLM-assisted Android forensic reports at the atomic-claim level. Gemini, Llama, and Qwen each generated reports f...

CVE-2026-109227

SGLang versions through 0.5.21 are vulnerable to an unbounded memory allocation vulnerability within the preprocess_video function in qwen_vl.py. The root cause is that the system decodes video frames at their full source resolution before applying max_pixels limits. A remote attacker can exploit...

PT-2026-110596

Name of the Vulnerable Software and Affected Versions SGLang versions prior to 0.5.22 Description An unbounded memory allocation issue exists in the preprocess video function within qwen vl.py. The system decodes video frames at their full source resolution before applying max pixels limits. Remo...

This Windows Malware is Built to Let Up to Four AI Models Vote on Its Next Move

A Windows malware called CLOSEDQUORUM is built to take orders from a vote of up to four AI models instead of an attacker's server, Cisco Talos said on September 22. The models can choose to steal Windows credentials, saved browser passwords, and crypto wallet data. Talos has not seen this setup...

MiST: Mid-Training LLMs for Cybersecurity

Cybersecurity combines high-stakes analysis with complex technical language, making it an impactful and challenging domain for LLMs. We present MiST Mid-trained Security Transformer, a suite of 8B and 32B models that achieve strong performance on public cybersecurity benchmarks. We use mid-traini...

Trust Me, I'M Your Developer: Self-Issued Authentication in Large Language Models

Large language model LLM security has largely focused on role-playing jailbreaks, with less attention to what happens when a user asks an LLM to verify an identity claim through a test designed by the model itself. We study this behavior through a staged developer-identity experiment with ChatGPT...

CVE-2026-82275

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...

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...

CVE-2026-82275 Qwen-Agent Arbitrary File Read via Caller-Supplied Document Path

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...

EUVD-2026-67806

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...

CVE-2026-82275

Qwen-Agent through 0.0.34 contains a path traversal vulnerability in its document parser (in simple_doc_parser.py and utils.py) that fails to restrict file access to intended directories. Because the Gradio interface is unauthenticated, an attacker can supply absolute file paths to read arbitrary...

CVE-2026-82275 Qwen-Agent Arbitrary File Read via Caller-Supplied Document Path

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...

CVE-2026-82275

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...

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...

CVE-2026-82268 Qwen-Agent Server-Side Request Forgery via Caller-Supplied Document URL

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-2026-82268

Qwen-Agent through 0.0.34 contains a server-side request forgery (SSRF) vulnerability in its document parsing path (qwen_agent/tools/simple_doc_parser.py). Caller-supplied paths are treated as URLs without scheme restriction or host validation , allowing an unauthenticated attacker to reach the G...

CVE-2026-82268 Qwen-Agent Server-Side Request Forgery via Caller-Supplied Document URL

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-2026-82268: Server-Side Request Forgery (SSRF)

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...