Evidence

Understanding and Mitigating Cross-Session Attacks via Persistent Artifacts in Agent Skill Composition

Unit 42: PHP2Shell exploitation and AI-like post-exploitation at European government

Unit 42 October 23 threat brief records post-exploitation at a European government, theft of authentication material, and command sequencing interpreted as signs of agentic attacker tooling; 22.6 million are potentially exposed instances, not victims.

Unitree Go2 CVE-2026-115995 advisory: chat_go set_volume command injection

Unitree Go2 CVE-2026-115995 advisory: chat_go set_volume command injection

US law-enforcement intelligence documents describe two arrests involving fabricated AI evidence given to police — original research or disclosure

Reported evidence for A reported review of law-enforcement records identifies two investigations involving manufactured images or videos submitted as evidence. Research intake: DB-RADAR-CP7-CP7A-077.

V12: 25 x402 vulnerabilities and three critical mechanisms

October 22 technical disclosure of spending authorization, cross-origin SIWE and Solana payment-verification flaws, with explicit limits of local testing.

Vercel: findings from the one-million-dollar Sandbox challenge

First-party disclosure separating a production-observed host memory leak, laboratory host execution, disk block reuse and cross-account snapshots.

vLLM advisory: EPS disguised as PNG reaches Ghostscript via Pillow

vLLM advisory: EPS disguised as PNG reaches Ghostscript via Pillow

vLLM code_revision override remote-code-execution advisory

vLLM CVE-2026-114053 code_revision override advisory with an offline import-time PoC, requiring a dynamic AutoProcessor and trust_remote_code. Affected 0.7.3 through 0.30.x, fixed 0.31.0.

vLLM maintainer advisory GHSA-6757-hggm-hp2w shared-memory handle forgery

vLLM maintainer advisory GHSA-6757-hggm-hp2w shared-memory handle forgery

vLLM P2pNcclConnector remote KV cache exfil by request ID

VulnCheck: IntentKit tool execution authorization bypass

CVE-2026-76066 analysis distinguishes hiding tools from users and enforcing permission at ToolNode execution.

VULONE: An exposed Cairn operator infrastructure

VULONE analyzes exposed Cairn operator records, access outcomes and human-directed agent workflows; its project counts are not an independent victim census.

WADE: An LSTM-Based Anomaly Detection Engine for WebAssembly Applications

WADE: An LSTM-Based Anomaly Detection Engine for WebAssembly Applications

Washington Post October 26: Cathedral tests Anthropic external business systems

Washington Post October 26: Cathedral tests Anthropic external business systems

What is Anthropic's policy for handling governmental requests for user information?

Anthropic says it does not disclose customer or end-user information in response to government requests except through valid legal process, such as a subpoena or warrant, unless it believes an emergency may result in imminent physical harm or death and immediate disclosure could avert it. Anthropic also says it evaluates requests for legal validity, may reject requests that are broad or vague, and generally gives users notice unless prohibited or a rare exception applies. For API or enterprise customer data, Anthropic says it will generally ask the requester to contact the customer first.

What You Sign Is Not What You Run: GGUF quantized model provenance audit

Liu and Tsai quantify missing environment provenance among the 198 most-downloaded in-scope GGUF repositories and demonstrate partial bit-exact reconstruction.

Where AI Vulnerability Discovery Harnesses Go Quiet

Commit-specific harness analysis with selection-stage demonstrations.

Who Verifies the Tools? How Warped Formatters Mislead Agents and Their Verifiers, William Jeffries

Who Verifies the Tools? How Warped Formatters Mislead Agents and Their Verifiers, William Jeffries

WIRED - Zoom screen-sharing takeover bug

Wiz incident reconstruction: Anatomy of a real AI-driven cloud attack

Wiz CIRT reconstructs a real cloud intrusion through an exposed Kafka UI, compromised cloud and IdP identities, and CI/CD or GitOps effects. The same IP scanned over 600 other environments, not 600 known breaches. The precise automation share and final exported data volume remain uncertain.

Wiz: LiteLLM 1.107.0 credential theft

Wiz traces malicious LiteLLM release artifacts, observed quarantine times and follow-on AWS/Bedrock reconnaissance, separately from vendor removal timestamps.

X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems

x402 foundation: per-payment spend controls for TypeScript clients

xAI: Grok Bot approvals, security and privacy

October 20 documentation of approval rules, shared per-user computer state and limits of model-based action review.

XBOW Labs: Zero to Calc in Six Days, full Chrome exploit chain

Technical Oct 13 research account of V8 Maglev, animated WebP and Crashpad issues, with a tested Windows sandbox-escape chain.

XRPL 3.4.1 coordinated disclosure: overflow and Batch wrapper validation

Original XRPL maintainer report on distinct XRP overflow and Batch inner-wrapper issues; credits Veria AI for the overflow report only. Checkpoints DB-RADAR-CP7-CP7A-052 and -053.

ZDI-26-648 / CVE-2026-19590

ZDI-26-649 / CVE-2026-19591