Security vulnerabilities, privacy incidents, safety concerns, and policy updates affecting LLMs and AI agents.
Claude Code, an agentic coding tool (AI that can write and execute code), had a sandbox escape vulnerability before version 2.1.64 where sandboxed processes could create symlinks (shortcuts pointing to files outside their designated area) that allowed writing to locations outside the workspace without user permission. An attacker could exploit this by injecting malicious instructions into Claude Code's input, potentially executing code outside the intended sandbox.
Fix: Update to Claude Code version 2.1.64 or later. The source states: 'Users on standard Claude Code auto-update have received this fix automatically. Users performing manual updates are advised to update to version 2.1.64 or later.'
NVD/CVE DatabaseLMDeploy, a toolkit for compressing, deploying, and serving large language models, contains a Server-Side Request Forgery vulnerability (SSRF, a flaw that lets attackers trick a server into making requests to unintended targets) in versions before 0.12.3. The vulnerability exists in the `load_image()` function, which downloads images from URLs without checking if those URLs point to private or internal systems, potentially allowing attackers to access sensitive cloud services and internal networks.
A vulnerability (CVE-2026-6662) was found in ericc-ch copilot-api versions up to 0.7.0 in the CORS function (a security feature that controls which websites can access an API from a web browser) of the token endpoint. The flaw allows a permissive cross-domain policy with untrusted domains, meaning attackers from other websites could potentially access the API remotely, and the exploit has been publicly disclosed.
A vulnerability (CVE-2026-6608) was found in lm-sys fastchat up to version 0.2.36 in the add_text function of the Arena Side-by-Side View Handler component, which allows incorrect control flow (improper program execution logic) that can be exploited remotely. The root cause was partially fixed in commit 34eca62 for one file, but three other files containing the same issue were not corrected.
A vulnerability was found in lm-sys fastchat (a tool for running AI models) up to version 0.2.36 that allows attackers to consume excessive resources by exploiting the api_generate function in the Worker API Endpoint (the part of the software that handles requests from other programs). The attack can be done remotely over the internet, the vulnerability details have been publicly disclosed, and it may already be exploited.
A security flaw called CVE-2026-6600 was found in Langflow (an AI tool) up to version 1.8.3 that allows cross-site scripting (XSS, where attackers inject malicious code into web pages to trick users). The vulnerability is in a React component (a reusable piece of code in the user interface) that handles message editing, and it can be exploited remotely by someone with login access.
A vulnerability exists in Langflow (an AI application framework) versions up to 1.8.3 in the Model Context Protocol Configuration API, where attackers can manipulate the X-Forwarded-For header (a field that identifies the client's IP address) to perform injection attacks (inserting malicious code into the system). This vulnerability can be exploited remotely, the exploit code is publicly available, and the vendor has not responded to disclosure attempts.
A vulnerability (CVE-2026-6598) was found in langflow-ai langflow versions up to 1.8.3 where the create_project/encrypt_auth_settings function improperly stores sensitive authentication settings in cleartext (unencrypted plain text) on disk instead of protecting them. An attacker can exploit this remotely, and the vulnerability details have been publicly disclosed.
A vulnerability (CVE-2026-6597) was found in langflow-ai langflow version 1.8.3 and earlier, where a function called remove_api_keys/has_api_terms fails to properly protect stored credentials (API keys and authentication information), allowing attackers to access them remotely. The vendor was notified but did not respond, and the exploit details have been publicly released.
A security vulnerability (CVE-2026-6596) was found in Langflow (an AI tool) version 1.1.0 and earlier, affecting a file upload function in the API. The flaw allows unrestricted file uploads (meaning attackers can upload any type of file without proper checks), and it can be exploited remotely without requiring authentication or user interaction.
Dagster had a SQL injection vulnerability (a security flaw where attackers can insert malicious SQL commands into database queries) in its database I/O managers (tools that read and write data to databases like DuckDB, Snowflake, and BigQuery). Users with permission to add dynamic partitions (flexible data groupings) could create partition keys that contained SQL commands, which would then execute against the database with the I/O manager's credentials, potentially allowing unauthorized data access or modification.
OpenTelemetry.Exporter.Jaeger has a memory exhaustion vulnerability where internal pooled lists (reusable memory structures) can grow too large based on big payloads and stay oversized for future use, potentially causing denial of service (making a system unavailable). However, the developers have no plans to fix this because the Jaeger exporter was deprecated in 2023.
Flowise versions up to 3.0.13 have a remote code execution vulnerability in the Airtable Agent node where user input is sent to an LLM (large language model, an AI that generates text) to generate Python code, which is then executed without proper sandboxing. An attacker can craft malicious prompts that trick the LLM into generating code containing dangerous commands (like imports or system operations) that bypass the validation checks, allowing them to run arbitrary code on the server without needing to log in.
OpenTelemetry eBPF Instrumentation (OBI) has a vulnerability where a local attacker controlling a Java process can overwrite arbitrary host files when Java injection is enabled and OBI runs with elevated privileges (special system permissions). The flaw occurs because the injector trusts an environment variable called TMPDIR from the target process without proper validation, and uses unsafe file creation methods that allow symlink attacks (where an attacker creates a link pointing to a different file to trick the system into overwriting it).
Claude Code on Windows had a security flaw where it loaded configuration files from a shared system directory without checking who owned that directory or had permission to change it. Since regular users could write to this directory by default, an attacker could create a malicious configuration file that would run with elevated privileges when another user launched Claude Code, allowing a local privilege escalation (unauthorized access to higher-level permissions).
QQBot media tags in the openclaw package could read arbitrary local files through reply text by referencing host-local paths outside the intended media storage boundary, allowing attackers to disclose local files through outbound media handling. This vulnerability affected openclaw versions before 2026.4.10.
FastGPT, an AI Agent building platform, has a vulnerability in its password change feature in versions before 4.14.9.5 where attackers can use NoSQL injection (inserting MongoDB operators into input fields to manipulate database queries) to bypass password verification and take over accounts without knowing the current password.
FastGPT, an AI Agent building platform, has a NoSQL injection vulnerability (a type of attack where an attacker tricks the database query by inserting special commands) in its login system before version 4.14.9.5. The vulnerability allows unauthenticated attackers to bypass password checks and log in as any user, including administrators, by sending database operators instead of a real password.
OpenClaw missed blocking dangerous environment variables (like VIMINIT, EXINIT, LUA_INIT, and HOSTALIASES) that could be set by users to change how programs start up or behave on the network. This security gap affected OpenClaw versions before 2026.4.10.
Flowise has a text-to-speech endpoint that doesn't require authentication but accepts a credential ID (an identifier for stored API keys like OpenAI or ElevenLabs) directly from user input. An attacker can use this to access someone else's stored API credentials and generate speech using the victim's API account, burning their API credits without permission.
Fix: Update LMDeploy to version 0.12.3 or later, which patches the issue.
NVD/CVE DatabaseFix: Install the patch identified by commit c9e84b89c91d45191dc24466888de526fa04cf33. Note that commit ff66426 patched the api_generate function in base_model_worker.py but missed other entry points (other places in the code where the same issue occurs).
NVD/CVE DatabaseFix: Update to the patched versions of Dagster. The fix ensures that partition key values are properly escaped before inclusion in SQL queries across all affected I/O managers. No configuration changes or workarounds are required alongside the update; only the Dagster code version needs to be updated. If unable to apply the update, manual workarounds are described in the referenced gist (https://gist.github.com/gibsondan/6d0c483f8499a8b1cd460cddc9fd8f72).
GitHub Advisory DatabaseFix: Prefer maintained exporters (for example OpenTelemetry Protocol format (OTLP)) instead of the Jaeger exporter.
GitHub Advisory DatabaseFix: Upgrade to https://github.com/open-telemetry/opentelemetry-ebpf-instrumentation/releases/tag/v0.8.0.
GitHub Advisory DatabaseFix: Users on standard Claude Code auto-update have already received this fix. Users performing manual updates are advised to update to the latest version.
GitHub Advisory DatabaseFix: Upgrade to openclaw version 2026.4.10 or newer. The latest npm release, 2026.4.14, already includes the fix. The fix enforces the media storage boundary for all outbound QQBot local file paths, which was implemented in PR #63271.
GitHub Advisory DatabaseFix: Update FastGPT to version 4.14.9.5 or later, where this issue has been fixed.
NVD/CVE DatabaseFix: This issue has been fixed in version 4.14.9.5. Users should upgrade to this version or later.
NVD/CVE DatabaseFix: Users should upgrade to openclaw version 2026.4.10 or newer. The latest npm release, openclaw@2026.4.14, already includes the fix, which expands the denylist (a list of blocked items) in the execution environment security policy to cover these high-risk environment variables.
GitHub Advisory DatabaseFix: Remove the TTS endpoint from the whitelist (the list of endpoints that don't need login), or add a check to ensure the credential ID matches the chatflow's TTS configuration. The source suggests: 'if (!chatflowId) { return res.status(401).json({ message: "Authentication required" }) }' — meaning if no chatflow ID is provided, the endpoint should reject the request with an authentication error.
GitHub Advisory Database