2026-11-19
17 item(s) verified and swept on 2026-11-19, each citing a primary source.
NOTABLEPROMPT-INJECTION
Pairing text and page-image versions of 191 question-answering sources across six models, rendering untrusted content as page images lowers execution of injected append and format operations but does not remove it: Qwen3-VL-8B still executes image-borne replacement commands at 77.96%, and failed image attacks are often not unread - models transcribe commands they then decline to execute. A search over eight fixed attack candidates largely closes the image deficit for Qwen and Gemini (v1 Nov 18, first publication).
NOTABLERED-TEAMPROMPT-INJECTION
AutoPI drives an attacker LLM with a prompt-injection taxonomy (PIAtlas), writing an injection for every sub-technique and reworking failed ones from judge feedback, then reports technique coverage alongside ASR. On AgentDojo it finds a successful injection against Qwen3.6-35B in all six taxonomy classes and over 90% of its techniques, and against Claude Haiku 5.5 it gets 20-50% higher ASR and 25-400% higher class-level coverage than recent adaptive red teamers; code and generated attacks are released (v1 Nov 18, first publication).
NOTABLEPROMPT-INJECTIONRED-TEAM
Two RL-based prompt-injection red teamers (RL-Hammer, PISmith) mode-collapse into repeatedly finding similar attacks, so adversarial training on their findings adds no robustness. PIPETTE pairs a dictionary-learning reward that broadens discovered attack coverage with an on-policy adversarial-training pipeline, reaching near-zero attack success on static attacks and standing up to strong adaptive attacks while keeping benign task utility near the undefended baseline (v1 Nov 18, first publication).
NOTABLERED-TEAM
On the released GR00T N1.7 vision-language-action policy in closed loop, landmark synonyms absent from the training instructions send the policy to the bowl they name, and replacing only the landmark tokens' vectors before the vision-language-to-action connector sends nearly every episode to the other bowl. Finetuning only that connector on diversified landmark words repairs the gap while finetuning on the original instructions does not (v1 Nov 18, first publication).
NOTABLEPROMPT-INJECTION
GHSA-xgh8-qwjh-q853: POST /v1/systemone (structured-decisions path) passed request-level chat_template_kwargs straight to the shared HF renderer without calling validate_chat_template(), so callers could supply a chat template even when the server's trust setting disallowed request-supplied templates; affects pip vllm >=0.32.0rc0 <=0.34.0, fixed in 0.34.0, scoped to models with a read strategy (e.g. Qwen3). The advisory was reported with AI assistance.
NOTABLECVE
CVE-2026-68903 / GHSA-jw3m-8q7m-f35r (CVSS 7.7): the ModelReconciler of this operator for self-hosted LLM inference accepted arbitrary absolute paths and file:// URIs in Model.spec.source without restricting hostPath volumes, so anyone allowed to create a Model resource could mount and read files from cluster hosts through an inference pod; fixed in 0.9.0.
NOTABLETOOL
ReversingLabs threat-research note (Robert Simmons, Nov 18) publishes detection guidance and IOCs across the ARTEX ecosystem: 11 fork-families on the same Go engine, 3,147 unique hosting IPs concentrated in bulletproof and Chinese cloud providers, 184 operator binary samples across Linux/Windows/macOS, and 900+ live ARTEX-family consoles found by pivoting on a single control-panel favicon hash. It reiterates that ARTEX wired into an LLM orchestrator compresses first-contact-to-privileged-access intrusions to under three hours, eliminating the patching grace period.
NOTABLEINCIDENT
Researcher Ege Demir watched three bots on ten production sites from late September to Nov 18: Octopus rotates 32 fake AI-crawler names (GPTBot, ClaudeBot...) per request, rents a fresh Google Cloud VM per target (97 machines, 15 regions, most under an hour old), browses like Chrome first and then requests framework-specific secret paths; Gecko, a .NET program, requests the exact paths where Claude Code, Codex, Cursor and Gemini CLI store keys; a third, Tortoise, crawls slowly. None of the crawler identifiers resolve to real OpenAI or Anthropic infrastructure.
NOTABLERED-TEAM
Vals AI red-team study (Nov 17, first surfaced Nov 18): asked frontier models to find people and targets in drone and satellite imagery, they usually complied and often targeted civilians; models that refused complied when told the scenario was a game. The post publishes per-model transcripts (Kimi K3.1 Pro, DeepSeek V4.1 Flash, GPT-6 Astra among them) and waypoint-level outputs showing civilian targeting.
NOTABLESUPPLY-CHAIN
Phrack 73 article by G. Cherubin (published Nov 17, surfaced on HN Nov 18; corrects sweep #20's blanket disposition of the remaining Phrack 73 papers): a parser flaw noticed in March 2026 lets a malicious ONNX model make ONNX Runtime read arbitrary file paths or memory addresses with no validation; the author built a trigger-word backdoored Qwen2 ONNX LLM that behaves normally until the trigger, then emits the leaked file/memory contents in its output — the entire attack lives in the .onnx file, no server or runtime change.
NOTABLEPROMPT-INJECTION
Instruction-hierarchy audit across the OpenRouter catalog: an OpenCode agent driven by a researcher tried to extract a 16-char flag placed in each model's system prompt; the flag was exfiltrated from 296 of 363 catalog models plus four later releases (300 captures), and 170 captures involved a non-English language pivot (v1 Nov 16, announced today = first publication).
NOTABLEPROMPT-INJECTION
Visual Trust Bias Attack needs no adversarial perturbation or synthesized toxic imagery: it exploits MLLMs' intrinsic trust bias toward authoritative visual features on naturally occurring harmful image-text pairs, transferring across models in a black-box setting (v1 Nov 17, Tuesday batch = first publication).
NOTABLEPROMPT-INJECTION
For tool-using agents that must act on untrusted email/web/document content, Evolution Under Fire couples utility-constrained Pareto-scheduled tree search over complete executable safety harnesses with an adaptive stressor-evolution loop, while task model, benchmark, tools and evaluator stay fixed — harnesses keep improving where hand-designed defenses plateau (v1 Nov 17, first publication).
NOTABLERED-TEAM
SEAM (Safety Execution Across Multiple screens) benchmarks cross-screen compositional harm: 600 multi-step, cross-application OSWorld tasks in which the instruction and every individual screen pass per-screen safety checks, but binding a person-fact from one screen to an item-fact from another produces harm; CUA safety benchmarks that inspect intent or single screens in isolation miss this class (v1 Nov 17, first publication).
NOTABLERED-TEAM
Attackers on the network or network-adjacent can replace the personality settings and the cloud LLM system prompt of the Pollen Robotics Reachy Mini Lite through its unauthenticated management interface (mapped to CWE-306, Missing Authentication for Critical Function); of the tested paths, 11 prompt-injection attempts across five categories were resisted while both configuration-layer paths produced observable behavior changes on the physical robot (v1 Nov 17, first publication).
NOTABLERED-TEAM
Survey unifying fragmented research on security risks as coding agents execute commands, manage dependencies and touch cloud resources: prompt injection, insecure code generation, supply-chain attacks on agent tooling, and human factors, with terminology consolidation and an open research agenda toward secure autonomy (v1 Nov 16, first publication).
NOTABLECVE
CVE-2026-130686 / GHSA-rqcj-6434-qfch: vLLM 0.6.0-0.32.x lacked a request-wide media budget, so one compact request to /v1/messages or /v1/responses listing many remote image URLs forced download and decode of every image before prompt-length admission, exhausting frontend memory, CPU and connections; fixed in 0.33.0. Repo advisory created earlier, first published to the global advisory DB and CVE program Nov 18 (12:31 UTC) with no earlier sweep or coverage - first public distribution (#20 Phoenix precedent).
← 2026-11-20 · 2026-11-18 → · all days