AI Security Dashboard
Curated vulnerabilities, advisories, and breaches affecting AI/ML systems.
Get the weekly digest
Top AI security stories every Monday. Free, no spam. Want it daily? See Daily Briefing.
CVE-2026-61808: LightRAG provides simple and fast retrieval-augmented generation. Through version 1.5.4, the LightRAG API server binds t
LightRAG provides simple and fast retrieval-augmented generation. Through version 1.5.4, the LightRAG API server binds to all network interfaces with authentication disabled by default, allowing an un...
CVE-2026-48039: Meta Ads MCP is a Model Context Protocol (MCP) server that lets AI assistants run Meta Ads. Prior to version 1.0.109, `A
Meta Ads MCP is a Model Context Protocol (MCP) server that lets AI assistants run Meta Ads. Prior to version 1.0.109, `AuthInjectionMiddleware.dispatch()` at `http_auth_integration.py:272` uncondition...
CVE-2026-71847: Ruby JSON is a JSON implementation for Ruby. From 2.20.0 until 2.21.2, Ruby's JSON native C extension clears the consume
Ruby JSON is a JSON implementation for Ruby. From 2.20.0 until 2.21.2, Ruby's JSON native C extension clears the consumed JSON::ResumableParser input buffer but leaves state.start, state.cursor, and s...
Ruby JSON: JSON::ResumableParser#partial_value dereferences a freed input buffer and crashes on truncated duplicate-key streams
### Summary Ruby's JSON native C extension clears the consumed `JSON::ResumableParser` input buffer but leaves `state.start`, `state.cursor`, and `state.end` pointing into released storage. When `pa...
Claude Code and Gemini CLI Flaws Let a GitHub Issue Reach CI Workflow Secrets
A GitHub issue opened by an account with no repository privileges was enough to execute code on the CI runners behind Anthropic's and Google's own coding-agent repositories. On OpenAI's, it was enough...
CVE-2026-12261: A vulnerability in `nltk.downloader` in nltk/nltk versions <= 3.9.4 allows for cross-package resource and model poisonin
A vulnerability in `nltk.downloader` in nltk/nltk versions
OpenAI rolls out a major ChatGPT upgrade, even if you don’t pay for it
OpenAI is rolling out a more reliable version of ChatGPT GPT-5.6 Sol for Plus and Pro users, while Free users are getting unlimited text chats with GPT-5.6 Luna. [...]
CVE-2026-70640: llama.cpp builds b1886 through b7445 contain a race condition use-after-free vulnerability in the LLaMA-Android JNI wrap
llama.cpp builds b1886 through b7445 contain a race condition use-after-free vulnerability in the LLaMA-Android JNI wrapper where bench_1model() and free_1context() lack synchronization, allowing Thre...
CVE-2026-70639: llama.cpp builds b1886 through b7445 contain a null pointer dereference vulnerability in the LLaMA-Android JNI wrapper w
llama.cpp builds b1886 through b7445 contain a null pointer dereference vulnerability in the LLaMA-Android JNI wrapper where the bench_1model() function fails to validate the model context pointer bef...
CVE-2026-70638: llama.cpp builds b1886 through b7445 contain an integer overflow vulnerability in the LLaMA-Android JNI wrapper where th
llama.cpp builds b1886 through b7445 contain an integer overflow vulnerability in the LLaMA-Android JNI wrapper where the new_1batch() function multiplies sizeof(llama_seq_id) by an attacker-controlle...
CVE-2026-67622: Flowise through 3.1.4 contains an insecure direct object reference vulnerability in the OpenAI Assistants integration th
Flowise through 3.1.4 contains an insecure direct object reference vulnerability in the OpenAI Assistants integration that allows authenticated attackers to access credentials belonging to other works...
CVE-2026-67621: Flowise through 3.1.4 contains a missing authorization vulnerability that allows authenticated workspace members to perf
Flowise through 3.1.4 contains a missing authorization vulnerability that allows authenticated workspace members to perform unauthorized document store operations by accessing unprotected mutation end...
CVE-2026-43632: llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six to
llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank,...
CVE-2026-43631: llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in the vocab pointer of llama-se
llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in the vocab pointer of llama-server when the --sleep-idle-seconds feature is enabled, allowing unauthenticated...
CVE-2026-43630: llama.cpp builds b5702 through b7653 contain an out-of-bounds read vulnerability in the recurrent memory state restore p
llama.cpp builds b5702 through b7653 contain an out-of-bounds read vulnerability in the recurrent memory state restore path that allows attackers with write access to the slot save directory to read m...
CVE-2026-43629: llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path whe
llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the state_read_data() function computes write size without overflow checking,...
CVE-2026-43628: llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sample
llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by se...
CVE-2026-43627: llama.cpp builds b1283 through b9058 contain an integer overflow vulnerability in the llama_batch_init() function where
llama.cpp builds b1283 through b9058 contain an integer overflow vulnerability in the llama_batch_init() function where unchecked multiplications in malloc() calls can wrap past INT32_MAX when computi...
CVE-2026-19111: Insecure direct object reference in the mongodb_memory, elasticsearch_memory, and mem0_memory tools in Amazon Strands Ag
Insecure direct object reference in the mongodb_memory, elasticsearch_memory, and mem0_memory tools in Amazon Strands Agents Tools before 0.8.3 might allow remote authenticated users to access, modify...
Traefik: Incomplete fix for CVE-2026-33433 + CVE-2026-39858 cross-cohort: headerField underscore-variant identity spoofing in BasicAuth / DigestAuth / ForwardAuth
## Summary There is a high severity vulnerability in Traefik's BasicAuth, DigestAuth, and ForwardAuth middlewares. The fix for CVE-2026-33433 stripped canonical-cased spoofed identity headers (e.g. `...
CVE-2026-43622: llama.cpp builds b1886 through b7445 contain a double free vulnerability in the LLaMA-Android JNI wrapper where new_1bat
llama.cpp builds b1886 through b7445 contain a double free vulnerability in the LLaMA-Android JNI wrapper where new_1batch() allocates memory using malloc() while free_1batch() deallocates it using th...
Meta AI model hacked a company during misconfigured cyber test
Meta has become the latest AI company to confirm that one of its models hacked a real organization during cybersecurity testing, as similar incidents continue to emerge following OpenAI'sOpenAI's init...
CVE-2026-19039: A vulnerability was detected in Kino-Kafkaesque ssh-mcp-server up to 8ebbbb99b26f80ff6162fe00957c6dec73fbc5a5. Impacted
A vulnerability was detected in Kino-Kafkaesque ssh-mcp-server up to 8ebbbb99b26f80ff6162fe00957c6dec73fbc5a5. Impacted is the function ssh_exec of the file src/index.ts of the component SSH Command H...
Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts
Zenity researchers reported the findings to Anthropic and OpenAI in late 2025 and early 2026, but they remain unpatched. The post Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via E...
AI Recommendation Poisoning: How "Ask AI" Buttons Silently Alter LLM Memory
A new class of prompt injection is spreading across commercial websites. It requires no malware, no stolen credentials, and no zero-day exploit. It abuses a standard feature built into almost every ma...