Evidence

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.

VeriCUA: Verification as Agentic Exploration for Computer-Using Agents

The paper reports 90.5 percent AndroidWorld verification accuracy for VeriCUA versus 78.4 percent for a vision-language judge, with VeriCUA deciding on 82 percent of that sample.

Veritas executes counterexamples against six popular agent benchmark graders and documents systematic false passes

Original Veritas paper constructs executable counterexamples against task graders and audits selected subsets of Agents' Last Exam, tau2-bench, DeepSWE and other benchmarks. It also tests generated replacement verifiers, with model- and harness-dependent results; sample findings are not whole-leaderboard error rates.

Vibe git log invoked repository-configured signature verifier before trust

CVE-2026-122135 relied on Git signature-verification settings during startup.

Vibe on Windows launched an attacker-controlled git.exe before repository trust

CVE-2026-122133 described project-local executable lookup before Safe Mode checks.

Vibe pre-trust git status ran configured Git filters

CVE-2026-122134 used local Git filter configuration before trust approval.

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 DeepSeek-OCR valid zero-sum image engine crash, CVE-2026-115914

Advisory reproducing fatal engine behavior on legitimate balanced black/white image content.

vLLM Jinja renderer CPU exhaustion, CVE-2026-115911

Advisory on unbounded tokenizer chat templates monopolizing a shared server-renderer worker.

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

vLLM permissive CORS and unauthenticated local inference, CVE-2026-115917

Advisory on browser-origin requests reaching loopback model serving without a configured API key.

vLLM Phi-4 audio encoder unbounded attention memory, CVE-2026-115913

Advisory showing a valid long audio input exhausting shared GPU memory in Phi-4 multimodal inference.

vLLM Responses API template trust-policy bypass, CVE-2026-115918

Advisory showing a distinct OpenAI-compatible endpoint missed request-template validation.

Voluntary Servitude: weaponized safety warnings

Study of attacker-written safety warnings in customer reviews and their effects on AI product recommendations.

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

Wells Fargo Online Access Agreement, forthcoming AI Agent terms effective November 24, 2026

Forthcoming Section 15 describes consent, recognition of AI-agent-initiated transactions, customer monitoring and revocation responsibilities, with explicit applicable-law exceptions. The version is dated effective November 24, 2026, not already in effect on November 9.

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

WikiTrace links reusable agent memories to complete original trajectories and lowers memory-induced regressions

Original WikiTrace paper evaluates linking condensed agent memories back to complete task trajectories across eight benchmark suites. Its reported utility gains are not a controlled test of forged traces, malicious memory injection or enterprise secret-retention safety.

WinWinHost: suspected TaskMarket staking trap in second task

Firsthand October 31 advisory reporting a separate affected agent wallet, task and hook references; aggregate loss figures remain allegations.

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.