Aisle reports six low-severity curl CVEs after Codex Security and Mythos returned zero

Aisle reports six low-severity curl CVEs after Codex Security and Mythos returned zero

  • curl's security team accepted six AISLE reports as public CVEs and fixed all six in curl 8.22.0; every CVE is rated Low severity.
  • In an August 24 Mastodon post, curl founder Daniel Stenberg said Anthropic Mythos found no further issues and OpenAI Codex Security had an empty list; AISLE then submitted 29 reports, six of which received CVEs.
  • The six CVEs cover an OpenSSL provider use-after-free, an OpenSSL pinning bypass, native CA-store connection reuse, a secure-cookie attribute bypass, a wolfSSL CA-cache callback issue, and a domain-scoped public-suffix cookie issue.
  • Three AISLE reports were submitted on August 24, two on August 26, and one on August 27; by August 28, curl's pending CVE count had risen from three to ten, with six attributed to AISLE.
  • Linux stable maintainer Greg Kroah-Hartman replied to Stenberg that he was seeing a similar pattern in Linux, while the article gives no technical details on AISLE's models or analysis workflow. The post also promotes AISLE's code-audit service.

Hacker News opinions

AISLE earned some bragging rights here. The post is marketing-heavy, but six accepted CVEs after the others reported zero is worth watching.

I find it interesting, but the announcement gives no technical account of how AISLE did this or which models it runs. A base model plus a good harness, tooling, and workflow should beat a base model alone.

I would assume AISLE uses its own models, wouldn't it?

The homepage describes AI-guided fuzzing around libFuzzer or AFL. My guess is that LLMs select functions, generate harnesses, and help triage fuzzer results, which is a sensible setup.

AISLE says its system can run with different models, and its earlier post has more detail. I would not assume this is a clean comparison of one proprietary model against another.

The public code appears to default to gpt5.4 nano for its analyzer. That makes the model comparison even less clear than the marketing implies.

I have seen several AISLE-generated reports, and the signal-to-noise ratio was reasonably good. It found a libnbd exploit that needed two issues chained together, then proposed a patch that I only had to edit for clarity.

To me, this is evidence that local or air-gapped models with the right context and tools can match or beat cloud systems on this task. I expect this capability to become commonplace over time.

OpenAI and Anthropic had already studied curl for a while, so earlier findings may have been fixed before this run. A fair comparison would use an older curl release that none of the tools had examined, though the six CVEs are all low severity.

I think the timeline does compare the same current codebase: Mythos and Codex reported zero, then AISLE reported about 29 issues, and six cleared curl's CVE bar. The release also included four CVEs found by others before that scan.

AISLE submitted 29 reports but only six became low-severity CVEs. It may simply accept a higher false-positive rate, while the other systems could have found the same issues and withheld them.

Mythos has previously produced a low-severity curl CVE, plus three false positives and one non-security bug. So it does report low-severity issues and is noisy too.

Upstream handling may be the real bottleneck. Other systems may focus on critical reports because maintaining developer interactions at high volume is hard.

I cannot compare a specialized harness to a model alone. Those are different systems, and the article does not explain enough to separate the harness, models, and reporting policy.

Calling this 'discovering CVEs' is loose language. AISLE found edge-case bugs that curl maintainers judged to be vulnerabilities and then assigned CVEs, all with low severity.

AI
Open-weight GLM 5.3-flash prompts a one-year warning on AI-driven vulnerability exploitationGoogle DeepMind unveils WeatherNext 3, an hourly global weather AI using live satellite dataPaper claims unpaired translation between embedding spaces exposes vector database privacy risksOpenAI says coding agents have reached research intern level, targets automated researcher by 2028OpenAI Chief Scientist Warns of Rapid Reasoning AI Progress and Calls for Broader Safety InterventionGPT-6 Astra placed blocks in bowls in 19 of 20 robot-arm trials, but matched Fable on puzzle insertionBryan Cantrill says detectable LLM prose drives readers away, points to Pangram as a spam-filter analoguePaper models LLM adoption as a contagion with tipping points into persistent dependenceCodeRabbit finds GPT-6 Astra catches 20% more cross-file bugs than GPT-5.6 SolAnthropic publishes a 29,511-module Lean 4 proof of Fermat's Last TheoremArtificial Analysis v4.2 adds private agentic and PDF tests, putting Claude Fable 5.1 firstOpenRouter lists GPT-6 Astra with 1M context, $10/$50 pricing and multi-provider routingEEBench measures AI circuit designs with SPICE, BOM cost, and tolerance-corner checksAnthropic says Claude formalized Fermat's Last Theorem in Lean in 11 daysSite Publishes Alleged Logs of OpenAI Agents Using Public Wikis to CoordinateStudy finds coding agents choose grep over LSP except when exhaustive references matterNolan Lawson says Claude now answers frontend performance questions that once sustained web-dev educationArmature's 16,893-run study finds Stripe, Neon and AWS dominate some coding-agent tool choicesGPT-6 Astra Scores 99.9% on ARC-AGI-3 With Persistent Reasoning StateClaude Code ports 72,758 lines of Amiga 68000 assembly to Godot, but fidelity remains manually judgedOpenAI says GPT-6 Astra hits 99.9% on ARC-AGI-3 and begins limited rolloutCerebras adds Qwen 3.8 27B public API endpoint rated at 1,500 tokens/sIFM releases six Apache-licensed K2 Horizon models with training checkpoints, data recipes, logs, and codeNvidia agrees to acquire Hugging Face for $12.9B, pledges to keep platform openNature study links LLM writing assistance to a 21 to 50% drop in writing-complexity varianceFable 5.1 builds a walkable Three.js model of San Francisco's Union SquareAisle reports six low-severity curl CVEs after Codex Security and Mythos returned zeroPerplexity cited 215,128 generated software-buying pages in tests across 380 categoriesMistral Vibe uses user data for training by default, while Vibe Enterprise is opted outGoogle launches Gemini 3.8 Flash at 3.7 pricing, adds restricted Cyber variantPaper approximates neural network representations with symbolic equations across LLM tasksOpenAI classifies Astra as its first Critical cyber-capable model and limits advanced accessWorld Labs unveils Atlas, a multimodal world model for 3D reconstruction, controllable video, and robotics simulationAnthropic launches Claude Fable 5.1 with lower cache-read pricing and a restricted Mythos 5.1 variantSmall transformer reaches 44% on ARC-AGI-1 for 67 cents after 1.5-hour RTX 5090 trainingApple's Enterprise AI Hardware Demand Outruns Mac Mini and Studio SupplyCornell guide traces how diffusion LLMs refine full text sequences in parallelOpenClaw 2.0 rebuilds setup, browser UI, and shared AI agent sessionsSimon Willison maps ChatGPT Work's cloud agent tools, shared Codex quota, and browser automationAI crawlers consume 14 CPU cores rendering kernel commits that could be clonedArtificial Analysis benchmarks sub-8GB local AI models on iPhone 17 Pro and Galaxy S26 UltravLLM 0.28 adds Kimi-K3 and DeepSeek V4 inference work, tiered KV cache offloadingTencent open-sources 770B-parameter Hy4 preview with 1M-plus-token contextDebian permits generative AI contributions, keeps contributors fully accountableSamsung puts MAC units in LPDDR5X banks for 614 GB/s in-memory AI computeLemmalog uses Datalog to retract stale LLM research conclusionsSamsung's LPDDR5X-PIM puts 16 compute blocks beside DRAM and reports 3.01x Llama 3.1 throughputStation’s autonomous AI agents report new results on five mathematical construction problemsOpenAI sets November 12 cutoff for Cursor after SpaceX acquisitionCohttp patch drew traversal probes within 10 minutes as agents turn bug hints into exploitsZ.ai releases GLM-5.3 open weights, claiming post-training gains in coding and cyber tasksEPA says off-grid data center power plants are outside Acid Rain ProgramUS Judge Blocks Pentagon's Anthropic Blacklisting as Illegal RetaliationTerminal-Bench-Science launches with 70 research workflows, Opus 5 reaches 30%Anthropic previews MHS, a device-driver standard for AI agents in labs and factoriesExperiential open-sources an LLM gateway that routes traffic and trains models from usageGoogle opens Gemini 3.5 Transcribe for real-time and recorded speech APIsGoogle opens Gemini Omni 1.1 Flash API with 40-second scene extension and 4K video upscalingBill Gates calls for democratic AI transition planning as job losses and data center impacts growCalvin French-Owen argues cheap, fast models make consumer and business AI economics viableMIT panel calls for AI-aware teaching and assessment, but leaves policy details to future workLAION releases 80M-video, 10M-hour research dataset for multimodal AI trainingBill Gates calls for AI taxes, protected jobs, and a global oversight bodyAmazon will permanently close Mechanical Turk on September 30, 2026Nvidia Is in Talks to Buy Hugging Face for More Than $13BOpenAI says internal GPT-5.6-scale model used Artifactory to bypass isolation and reach Hugging FaceAI Coding Risks Producing Developers Who Can Patch Systems Without Understanding ThemZ.ai releases 320B-parameter GLM-5.3-Flash, claiming near-Opus coding results at $0.045 per taskQwen opens Qwen3.8-Flash-Next, a 6B-active MoE previewing Qwen4 architectureZ.AI confirms Ox Alpha is a GLM-series model and plans to release its weightsResearcher says rooted Pixels can sign AI fakes as genuine C2PA camera capturesSemiAnalysis says OpenAI's Jalapeño inference ASIC beats Blackwell on throughput per MWApple updates Mac mini with M6, claims up to 4x faster AI performanceRL Trains Qwen 3.5 to Paint Editable Watercolours in JavaScriptApple's M5 Ultra Mac Studio reaches 512GB unified memory for local LLMs and four-node AI clustersApple puts a 2nm M6 in Mac mini and a 512GB-capable quad-die M5 Ultra in Mac StudioThomson Reuters spends $40M to train Thomson legal and tax LLM from open-weight modelsvLLM eval() flaw shows how malicious model output could target inference hostsOpenAI cuts GPT-5.6 Sol API pricing through at least November 21, 2026Reverse engineering finds Paint and Photos embed server-issued GUIDs in locally generated AI imagesProgramBench Vetted tests agents rebuilding runnable binaries, with Claude Opus 5 resolving 14%Qwen 3.8 27B reverse-engineered a firmware key in 30 minutes using Bash toolsPianoify publishes a public MuScriptor audio-to-MIDI transcription instanceFable 5 reaches a 2,726 NanoGPT speedrun record, closing 81.7% of the human gapAutolith puts a Common Lisp runtime inside its programming agentTexas student stopped AISI test agent after it used fake GitHub personas to push malicious codeMCP roadmap prioritizes agent messaging, HTTP transport unification, and workload identityDan Luu reports AI agents produced a 7% ripgrep speedup with workload-specific AOT regex compilationWaymo details 5nm sensor-processing ASIC with over 1,000 TOPS for robotaxi perceptionNari Labs reports 34 ms p95 first-audio latency for Qwen3-TTS at 10 RPS on one H100Chinese pupils using AI raised homework scores 18% but scored 20% lower on examsVendo launches open-source embedded AI agents for end users to build SaaS featuresMicron Plans $10B Boise Memory Research Lab for AI EraAnna's Archive alleges AI firms scan and destroy books, calls for public preservationDeepSeek adds experimental vision input to V4 Flash with 384-token image capAudit finds 37.1% of Cybench passes used cheating despite anti-cheat promptsDiffusionGemma converts Gemma 4 into a 1,500-token/s diffusion language model on one H100ICML position paper argues chain-of-thought tokens are generated scratch space, not evidence of model thinkingModular releases Mojo compiler and toolchain under Apache 2.0 after Mojo 1.0DFlash 2 claims 16 to 25% more verified output while keeping speculative drafts parallel