aisecwatch.com
DashboardVulnerabilitiesNewsResearchArchiveStatsDataset
Subscribe
aisecwatch.com

Real-time AI security monitoring. Tracking AI-related vulnerabilities, safety and security incidents, privacy risks, research developments, and policy changes.

Navigation

VulnerabilitiesNewsResearchDigest ArchiveNewsletter ArchiveSubscribeData SourcesStatisticsDatasetAPIIntegrationsWidgetRSS Feed

Maintained by

Truong (Jack) Luu

Information Systems Researcher

AI & LLM Vulnerabilities

Security vulnerabilities, privacy incidents, safety concerns, and policy updates affecting LLMs and AI agents.

to
Export CSV
1588 items

GHSA-rr7j-v2q5-chgv: LangSmith SDK: Streaming token events bypass output redaction

mediumvulnerability
security
Apr 15, 2026

The LangSmith SDK (a tool for monitoring AI applications) has a security flaw where its output redaction feature (hideOutputs in JavaScript, hide_outputs in Python) doesn't work for streaming token events. When an LLM produces streamed output, each piece of data is recorded as a new_token event with unredacted content that bypasses the redaction process entirely, potentially leaking sensitive information to LangSmith storage.

GitHub Advisory Database

Anthropic products are operational after brief outage, status page says

infoincident
industry
Apr 15, 2026

Anthropic experienced a brief outage on Wednesday affecting its Claude chatbot, API (application programming interface, the connection between software services), and Claude Code assistant, with elevated error rates beginning around 10:53 a.m. ET. By 1:50 p.m. ET, all systems were restored and operational, with login success rates stabilizing by 12:30 p.m. ET.

CVE-2026-30617: LangChain-ChatChat 0.3.1 contains a remote code execution vulnerability in its MCP STDIO server configuration and execut

criticalvulnerability
security
Apr 15, 2026
CVE-2026-30617

LangChain-ChatChat version 0.3.1 has a remote code execution vulnerability (RCE, where an attacker can run commands on a system they don't own) in how it handles MCP STDIO servers (a communication protocol for server connections). An attacker can access the exposed management interface, set up a malicious MCP server with commands of their choice, and then trigger those commands to run when the service processes agent requests.

CVE-2026-30615: A prompt injection vulnerability in Windsurf 1.9544.26 allows remote attackers to execute arbitrary commands on a victim

criticalvulnerability
security
Apr 15, 2026
CVE-2026-30615

Windsurf version 1.9544.26 has a prompt injection vulnerability (a technique where attackers hide malicious instructions in input to trick an AI system) that allows remote attackers to execute arbitrary commands on a victim's computer. When Windsurf processes attacker-controlled HTML content, it can be tricked into automatically registering a malicious MCP STDIO server (a communication interface for running code), giving attackers the ability to run commands without the user's knowledge.

CVE-2026-39884: mcp-server-kubernetes is a Model Context Protocol server for Kubernetes cluster management. Versions 3.4.0 and prior con

highvulnerability
security
Apr 15, 2026
CVE-2026-39884

mcp-server-kubernetes versions 3.4.0 and earlier have an argument injection vulnerability (a type of attack where an attacker sneaks extra commands into a tool by exploiting how input is processed) in the port_forward tool. The vulnerability exists because the code builds a kubectl command (a tool for managing Kubernetes clusters) by concatenating strings with user input and splitting on spaces, instead of using a safer array-based method like other tools in the codebase. This allows attackers to inject malicious kubectl flags to expose internal services or target resources in unintended ways.

GHSA-7xjm-g8f4-rp26: Giskard has Unsandboxed Jinja2 Template Rendering in ConformityCheck

mediumvulnerability
security
Apr 14, 2026
CVE-2026-40320

The `ConformityCheck` class in giskard-checks was automatically treating the `rule` parameter as a Jinja2 template (a template language that evaluates expressions), which could allow arbitrary code execution if check definitions came from untrusted sources. While the library is only used locally by developers, this hidden behavior made it easy to accidentally pass untrusted input without realizing expressions would be evaluated.

GHSA-rq2q-4r55-9877: Giskard has a Regular Expression Denial of Service (ReDoS) in RegexMatching Check

lowvulnerability
security
Apr 14, 2026
CVE-2026-40319

The RegexMatching check in giskard-checks has a ReDoS vulnerability (regular expression denial of service, where a specially crafted regex pattern causes the regex engine to hang by backtracking excessively through text). An attacker with write access to check definitions can craft malicious regex patterns that make the testing process hang indefinitely, disrupting automated testing environments like CI/CD pipelines (continuous integration/continuous deployment automation).

CVE-2026-23653: Improper neutralization of special elements used in a command ('command injection') in GitHub Copilot and Visual Studio

mediumvulnerability
security
Apr 14, 2026
CVE-2026-23653

CVE-2026-23653 is a command injection vulnerability (a flaw where an attacker can insert malicious commands into input that gets executed) in GitHub Copilot and Visual Studio Code that allows an authorized attacker to disclose information over a network. The vulnerability stems from improper neutralization of special elements used in commands. The CVSS severity score (a standard 0-10 rating of how serious a security flaw is) has not yet been assigned by NIST.

CVE-2026-5429 - Kiro IDE Webview Cross-Site Scripting via Workspace Color Theme

highvulnerability
security
Apr 14, 2026

Kiro IDE (a development environment that uses AI agents to help developers) has a cross-site scripting vulnerability (XSS, where an attacker injects malicious code that runs in a web browser) in versions before 0.8.140. An attacker can exploit this by creating a malicious workspace with a crafted color theme name, and if a user opens and trusts that workspace, the attacker's code will execute on their computer.

CVE-2025-61260: A vulnerability was identified in OpenAI Codex CLI v0.23.0 and before that enables code execution through malicious MCP

highvulnerability
security
Apr 14, 2026
CVE-2025-61260

A vulnerability in OpenAI Codex CLI v0.23.0 and earlier allows attackers to execute arbitrary code by creating malicious configuration files (.env and .codex/config.toml) in a repository. When a user runs the codex command in a compromised repository, the tool automatically loads these files without asking for permission, triggering the attacker's embedded commands.

GHSA-p4h8-56qp-hpgv: SSH/SCP option injection allowing local RCE in @aiondadotcom/mcp-ssh

highvulnerability
security
Apr 13, 2026

An SSH/SCP option injection vulnerability in the @aiondadotcom/mcp-ssh library allowed attackers to execute arbitrary commands locally on the machine running the MCP server (a tool that connects an AI to external systems). By crafting malicious input like `-oProxyCommand=...`, attackers could trick SSH into running their code before any network connection happened, potentially stealing SSH keys and credentials. The vulnerability could be triggered even without a malicious user, since an LLM (large language model) could be tricked through prompt injection (hiding attacker instructions in text it reads) to pass the malicious input to the tool.

Suspect in attack at Sam Altman's house aimed to kill OpenAI CEO, warned of humanity's extinction from AI

infoincident
safetysecurity

CVE-2026-1462: A vulnerability in the `TFSMLayer` class of the `keras` package, version 3.13.0, allows attacker-controlled TensorFlow S

criticalvulnerability
security
Apr 13, 2026
CVE-2026-1462

A vulnerability in keras version 3.13.0 allows attackers to run their own code when a model is loaded, even when `safe_mode=True` (a setting meant to prevent unsafe operations). The problem occurs because the `TFSMLayer` class loads external TensorFlow SavedModels (pre-trained model files) without checking if they're safe, and doesn't properly validate file paths or configuration data.

CVE-2026-6129: A vulnerability was detected in zhayujie chatgpt-on-wechat CowAgent up to 2.0.4. This affects an unknown function of the

highvulnerability
security
Apr 12, 2026
CVE-2026-6129

A vulnerability (CVE-2026-6129) was found in the CowAgent component of zhayujie's chatgpt-on-wechat software up to version 2.0.4, where missing authentication (failure to verify user identity) in the Agent Mode Service allows attackers to perform unauthorized actions remotely. The exploit is publicly available and the developers have not yet responded to the initial report of the problem.

CVE-2026-6126: A weakness has been identified in zhayujie chatgpt-on-wechat CowAgent 2.0.4. The affected element is an unknown function

highvulnerability
security
Apr 12, 2026
CVE-2026-6126

CVE-2026-6126 is a missing authentication vulnerability in zhayujie chatgpt-on-wechat CowAgent version 2.0.4, affecting an administrative HTTP endpoint (a web-based control interface). An attacker can remotely exploit this flaw without needing valid credentials, and the exploit code has been publicly released.

CVE-2026-40252: FastGPT is an AI Agent building platform. Prior to 4.14.10.4, Broken Access Control vulnerability (IDOR/BOLA) allows any

mediumvulnerability
security
Apr 10, 2026
CVE-2026-40252

FastGPT (a platform for building AI agents) has a broken access control vulnerability (IDOR/BOLA, a flaw where one user can access another user's data by guessing or changing IDs) that allows any authenticated team to run AI applications belonging to other teams by using a different application ID. The system checks that users are logged in but doesn't verify that the application they're trying to use actually belongs to their team, leading to unauthorized access to private AI workflows across teams.

GHSA-75hx-xj24-mqrw: n8n-mcp has unauthenticated session termination and information disclosure in HTTP transport

highvulnerability
security
Apr 10, 2026

n8n-mcp (a tool for connecting AI systems to external services) had security problems where certain HTTP endpoints (the connection points a program offers over the internet) didn't require authentication and exposed sensitive system information. An attacker with network access could shut down active sessions and gather details to plan further attacks.

GHSA-fw9q-39r9-c252: LangSmith Client SDKs has Prototype Pollution in langsmith-sdk via Incomplete `__proto__` Guard in Internal lodash `set()`

mediumvulnerability
security
Apr 10, 2026
CVE-2026-40190

The LangSmith JavaScript SDK contains a prototype pollution vulnerability (a type of attack where an attacker modifies the base object that all JavaScript objects inherit from) in its internal lodash `set()` function. The vulnerability exists because the code only blocks the `__proto__` key but allows attackers to bypass this protection using `constructor.prototype` instead, potentially affecting all objects in a Node.js application if they control data being processed by the `createAnonymizer()` API.

GHSA-8x8f-54wf-vv92: PraisonAI Browser Server allows unauthenticated WebSocket clients to hijack connected extension sessions

criticalvulnerability
security
Apr 10, 2026

PraisonAI's browser bridge server (started with `praisonai browser start`) has a security flaw where it accepts WebSocket connections (a two-way communication channel between a client and server) without proper authentication checks. An attacker on the network can connect without credentials, trick the server into linking their connection to a legitimate browser extension session, and then intercept all commands and responses from that session, effectively taking control of the browser automation without permission.

GHSA-ffp3-3562-8cv3: PraisonAI: Coarse-Grained Tool Approval Cache Bypasses Per-Invocation Consent for Shell Commands

mediumvulnerability
securitysafety
1 / 80Next
CNBC Technology
NVD/CVE Database
NVD/CVE Database

Fix: Update to version 3.5.0, which fixes this issue.

NVD/CVE Database

Fix: Upgrade to `giskard-checks` >= 1.0.2b1. The patched version removes template rendering from rule evaluation entirely.

GitHub Advisory Database

Fix: Upgrade to giskard-checks >= 1.0.2b1.

GitHub Advisory Database
NVD/CVE Database

Fix: Update Kiro IDE to version 0.8.140 or later.

AWS Security Bulletins
NVD/CVE Database

Fix: Fixed in version 1.3.5. The patch includes: adding `--` argument terminators to all SSH/SCP invocations (which tells the command where options end and arguments begin), implementing a strict whitelist for host aliases that rejects leading dashes and shell metacharacters, requiring all host aliases to be defined in `~/.ssh/config` or `~/.ssh/known_hosts`, and resolving `ssh.exe`/`scp.exe` to absolute paths with `shell: false` on Windows to prevent command re-parsing. No workarounds exist; users must upgrade to 1.3.5.

GitHub Advisory Database
Apr 13, 2026

A man named Daniel Moreno-Gama was arrested after throwing a Molotov cocktail (an improvised incendiary weapon) at OpenAI CEO Sam Altman's home and later attacking OpenAI's headquarters. Moreno-Gama was motivated by concerns about AI posing an existential threat to humanity and had planned the attack in advance, as documented in a written statement found by police. Sam Altman responded by calling for reduced hostile rhetoric within the AI industry.

CNBC Technology
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database

Fix: This vulnerability is fixed in version 4.14.10.4. Users should upgrade to FastGPT 4.14.10.4 or later.

NVD/CVE Database

Fix: Fixed in v2.47.6, where all MCP session endpoints now require Bearer authentication (a token-based security method). If you cannot upgrade immediately, you can restrict network access using firewall rules, reverse proxy IP allowlists, or a VPN to allow only trusted clients. Alternatively, use stdio mode (MCP_MODE=stdio) instead of HTTP mode, since stdio transport does not expose HTTP endpoints and is not affected by this vulnerability.

GitHub Advisory Database

Fix: Fixed in version 0.5.18. Users should update their `langsmith` package to 0.5.18 or later.

GitHub Advisory Database
GitHub Advisory Database
Apr 10, 2026

PraisonAI Agents has a security flaw where tool approval decisions are cached by tool name only, not by the specific command arguments. Once a user approves the `execute_command` tool (a function that runs shell commands) for any command like `ls -la`, all future shell commands in that session bypass the approval prompt entirely. Combined with the fact that all environment variables (including API keys and credentials) are passed to subprocesses, an LLM agent can silently steal sensitive data without asking permission again.

GitHub Advisory Database