Agentic / MCP
653 entries
Every Agentic / MCP entry VulnWatch has indexed, sorted by publication date.
Subscribe to this tag's RSS feed
CVE-2026-47128: nono is software that allows users to run AI agents in a zero-latency sandbox. Prior to version 0.55.0, the nono Landloc
nono is software that allows users to run AI agents in a zero-latency sandbox. Prior to version 0.55.0, the nono Landlock/seccomp policies allow access to local Unix domain sockets (concrete and abstr...
Cursor, Codex, Gemini CLI, Antigravity hit by sandbox escapes
Researchers escaped the sandboxes in Cursor, Codex, Gemini CLI and Antigravity by having the AI agent write files that trusted host tools later run. Multiple CVEs, patches, and Google downgrading two...
JadePuffer agentic attacks now target AI model data with ransomware
The JadePuffer autonomous AI agent has upgraded with custom malware called EncForge that focuses on encrypting AI assets, such as training datasets, vector databases, and model checkpoints. [...]
FakeGit Campaign Uses 7,600 GitHub Repositories to Spread SmartLoader Malware
Cybersecurity researchers have discovered nearly 7,600 malicious GitHub repositories, out of which more than 800 pose as artificial intelligence (AI) skills or Model Context Protocol (MCP) servers to...
CVE-2026-46555: WhatsApp MCP Server is a Model Context Protocol (MCP) server for WhatsApp, enabling Claude to read and send WhatsApp mes
WhatsApp MCP Server is a Model Context Protocol (MCP) server for WhatsApp, enabling Claude to read and send WhatsApp messages. Prior to version 0.2.1, the `whatsapp-bridge` HTTP API listens on `127.0....
Hugging Face warns an autonomous AI agent hacked its network
The Hugging Face artificial intelligence repository disclosed that attackers gained access to internal datasets and credentials after breaching its production infrastructure using an autonomous AI age...
Capital One Open Sources AI-Powered ‘VulnHunter’ Security Tool
The agentic security tool identifies potentially exploitable code flaws, traces attack paths, and recommends targeted remediations. The post Capital One Open Sources AI-Powered ‘VulnHunter’ Security T...
World's Largest AI Model Repository Hugging Face Breached by Autonomous AI Agent
In an ironic twist, open-source artificial intelligence (AI) platform Hugging Face revealed that it was the victim of a hack perpetrated by an autonomous AI agent system. The company said it detected...
CVE-2026-7755: IBM Langflow OSS 1.0.0 through 1.10.0 Langflow could allow remote code execution due to incomplete validation enforcemen
IBM Langflow OSS 1.0.0 through 1.10.0 Langflow could allow remote code execution due to incomplete validation enforcement on MCP server configuration files.
CVE-2026-15995: IBM Cognos Analytics 12.1.3 GA Version with build number through 12.1.3-2606251736 could allow an attacker to obtain inc
IBM Cognos Analytics 12.1.3 GA Version with build number through 12.1.3-2606251736 could allow an attacker to obtain incorrect report summary results or cause report-processing failures due to a race...
CVE-2026-15415: AWS HealthOmics is a HIPAA-eligible service that fully manages the compute, storage, and workflow engine infrastructure
AWS HealthOmics is a HIPAA-eligible service that fully manages the compute, storage, and workflow engine infrastructure required to run bioinformatics analyses at scale for clinical diagnostics, drug...
CVE-2026-14501: IBM Db2 Genius Hub 1.1, 1.1.1, 1.1.2 and IBM Agentics 1.0 could allow an attacker to execute arbitrary code or obtain se
IBM Db2 Genius Hub 1.1, 1.1.1, 1.1.2 and IBM Agentics 1.0 could allow an attacker to execute arbitrary code or obtain sensitive information due to the use of dangerous functions without sufficient res...
mcp-memory-keeper: Arbitrary local file read in context_import via unvalidated filePath
### Impact `context_import` passed the caller-supplied `filePath` directly to `fs.readFileSync` with no path confinement. A malicious MCP client — or an LLM agent that is prompt-injected into calling...
CVE-2026-9135: IBM Langflow OSS 1.0.0 through 1.10.0 Langflow versions up to 1.9.2 (commit 94981c443d4918517b9e8163d70fc598dc33a32d) co
IBM Langflow OSS 1.0.0 through 1.10.0 Langflow versions up to 1.9.2 (commit 94981c443d4918517b9e8163d70fc598dc33a32d) contain a code injection vulnerability in the Policies component's ToolGuard integ...
CVE-2026-58195: Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone
Agentic-Flow is an AI agent orchestration platform. Prior to 2.0.14, agentic-flow MCP server tools in src/mcp/standalone-stdio.ts, src/mcp/fastmcp/servers/claude-flow-sdk.ts, src/mcp/fastmcp/servers/s...
oapi-codegen: OpenAPI Server Description Escapes Generated Go Comment and Injects Executable Code
## Summary The vulnerability in oapi-codegen seems to be similar with CVE-2026-22785, which is a generated-code injection issue where untrusted OpenAPI `summary` text is embedded into generated Type...
meta-ads-mcp: X-Pipeboard-Token Header Auth Bypass Reuses Operator Meta Token
## X-Pipeboard-Token Header Auth Bypass Reuses Operator Meta Token ### Summary `AuthInjectionMiddleware` in `meta-ads-mcp` rejects HTTP MCP requests only when **both** `auth_token` and `pipeboard_to...
meta-ads-mcp: Server-Side Request Forgery (SSRF) in `upload_ad_image` via Unrestricted `image_url` Fetch
## Server-Side Request Forgery (SSRF) in `upload_ad_image` via Unrestricted `image_url` Fetch ### Summary The `upload_ad_image` MCP tool in `meta-ads-mcp` v1.0.113 passes an attacker-controlled `ima...
CVE-2026-57860: ForgeCode (tailcallhq/forgecode), an AI pair-programming CLI, automatically loads and executes the MCP servers defined i
ForgeCode (tailcallhq/forgecode), an AI pair-programming CLI, automatically loads and executes the MCP servers defined in a repository's .mcp.json file on startup without user confirmation. A maliciou...
In Other News: Iran Tracks US Military Phones, CrashStealer macOS Malware, CVD Blueprint
Noteworthy stories that might have slipped under the radar: OpenClaw AI agents exploited via WhatsApp, ransomware hits naval defense firm TKMS, Lidl discloses data breach. The post In Other News: Iran...
Podcast: Broken Governance, Agentic AI, and the MindStone Agent Exclusive
(Video) Artificial intelligence is transforming cybersecurity, but are governance, compliance, and security practices evolving fast enough to keep up? The post Podcast: Broken Governance, Agentic AI,...
MCP Python SDK: WebSocket server transport does not support Host/Origin validation
### Summary In affected versions, the deprecated WebSocket server transport (`mcp.server.websocket.websocket_server`) accepted the WebSocket handshake without applying any `Host` or `Origin` header va...
CVE-2026-46341: The Apify MCP server enables AI agents to extract data from websites using ready-made scrapers, crawlers, and automation
The Apify MCP server enables AI agents to extract data from websites using ready-made scrapers, crawlers, and automation tools available on the Apify Store. Prior to 0.9.21, the fetch-apify-docs tool...
CVE-2026-44970: dbt-mcp is a Model Context Protocol server for interacting with dbt. Prior to 1.17.1, DefaultUsageTracker.emit_tool_call
dbt-mcp is a Model Context Protocol server for interacting with dbt. Prior to 1.17.1, DefaultUsageTracker.emit_tool_called_event() in src/dbt_mcp/tracking/tracking.py serialized every MCP tool call's...
CVE-2026-44969: dbt-mcp is a Model Context Protocol server for interacting with dbt. Prior to 1.17.1, DbtMCP.call_tool() in src/dbt_mcp/
dbt-mcp is a Model Context Protocol server for interacting with dbt. Prior to 1.17.1, DbtMCP.call_tool() in src/dbt_mcp/mcp/server.py logged the raw arguments dictionary at INFO level before each tool...