Agentic / MCP
653 entries
Every Agentic / MCP entry VulnWatch has indexed, sorted by publication date.
Subscribe to this tag's RSS feed
AI-powered attack exploited PaperCut flaws to hack 395 organizations
A threat actor, likely Russian-speaking, used hundreds of AI agents to develop and launch a global exploitation campaign targeting vulnerable PaperCut NG/MF servers. [...]
PaperCut Attacker Uses Hundreds of AI Agents to Compromise 440+ Instances
A suspected Russian-speaking cyber actor has been attributed to the use of artificial intelligence (AI) to devise exploits targeting a recently disclosed pair of security flaws in PaperCut NG/MF and b...
Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6
Anthropic on Wednesday disclosed a fourth incident in which its artificial intelligence (AI) model broke into real third-party systems, marking the latest in a growing list of cases that have raised c...
functype-mcp-server: MCP `set_functype_version` Package Alias RCE via Unsanitized pnpm install + Dynamic Import
## MCP `set_functype_version` Package Alias RCE via Unsanitized pnpm install + Dynamic Import ### Summary The `set_functype_version` MCP tool in `functype-mcp-server` accepts an unconstrained `versi...
CVE-2026-87911: An OS command injection weakness in the read-only enforcement of the SQL validation component in Amazon awslabs postgres
An OS command injection weakness in the read-only enforcement of the SQL validation component in Amazon awslabs postgres-mcp-server before 1.1.7 might allow an unauthenticated actor to execute operati...
HelmGuard Raises $7.3 Million for Agentic GRC and Security
The company will increase its US market presence and will expand its engineering and go-to-market teams. The post HelmGuard Raises $7.3 Million for Agentic GRC and Security appeared first on SecurityW...
Meta Launches Personal AI Agent, Muse, Emphasizes Safety and Privacy
Muse runs on a dedicated, secure virtual machine that houses both the agent and the user’s data. The post Meta Launches Personal AI Agent, Muse, Emphasizes Safety and Privacy appeared first on Securit...
DeepSeek Harness Flaw Let AI Agents Disable Their Own File Sandbox Without Approval
A flaw in DeepSeek Harness, DeepSeek's open-source tool for running AI coding agents on a developer's machine, let a sandboxed agent turn off its own sandbox with a single command. The tool runs an a...
CVE-2026-53937: MCP Kotlin SDK is the Kotlin Multiplatform software development kit for the Model Context Protocol. In versions 0.7.0 th
MCP Kotlin SDK is the Kotlin Multiplatform software development kit for the Model Context Protocol. In versions 0.7.0 through 0.12.0, `ReadBuffer.append` in `kotlin-sdk-core/src/commonMain/kotlin/io/m...
The Hidden Instructions That Can Hijack AI Agents
Malicious prompts concealed in documents, metadata, emails, images and code can manipulate autonomous agents into taking dangerous actions. The post The Hidden Instructions That Can Hijack AI Agents a...
Autonomous AI Agents Compromise Thousands of Credentials in Under Six Hours
Threat actors are continuing to leverage artificial intelligence (AI) to streamline their operations, with one financially motivated hacking group employing an autonomous, multi-agent attack framework...
OpenAI admits it didn't disclose rogue AI wiki hijacking incident
OpenAI admits it did not disclose an incident where autonomous AI agents hijacked a German wiki, created 18,000 posts, shared answers, and bypassed restrictions, saying it treated the activity as mode...
CVE-2026-86122: Rowboat through 0.9.1 fails to validate custom MCP server and webhook URLs, allowing authenticated users to configure ar
Rowboat through 0.9.1 fails to validate custom MCP server and webhook URLs, allowing authenticated users to configure arbitrary destinations. Attackers can point these URLs at internal services and cl...
Thousands of OpenAI Agents Quietly Turned an Abandoned Wiki Into Their Coordination Channel
A group of AI safety researchers says a fleet of autonomous agents that identified themselves as OpenAI systems left about 18,000 posts on a dormant 25-year-old German wiki between May and July 2026,...
CVE-2026-85787: An incomplete list of disallowed inputs in the SQL validation component in Amazon awslabs postgres-mcp-server before ve
An incomplete list of disallowed inputs in the SQL validation component in Amazon awslabs postgres-mcp-server before version 1.1.7 might allow an unauthenticated actor to modify data beyond the read-...
CodeWhale: js_execution leaks parent environment to model context via missing env scrub
### Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 26de44a8bd5051f...
CodeWhale: image_analyze follows workspace symlinks, leaking external file bytes
### Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 26de44a8bd5051f...
CVE-2026-19645: IBM MQ Agent CD: v1.0.0, v1.0.1, v2.0.0, v2.0.1 An authenticated user with a valid session cookie can submit arbitrarily
IBM MQ Agent CD: v1.0.0, v1.0.1, v2.0.0, v2.0.1 An authenticated user with a valid session cookie can submit arbitrarily large or computationallyexpensive requests that cause the LLM agent workers to...
Orval: RCE via OpenAPI path -> unescaped request-URL template literal (backtick breakout)
### Summary Orval emits the OpenAPI path into the generated request URL as a TEMPLATE LITERAL (`` `/users/...` ``) without escaping the backtick character. A path containing a backtick closes the tem...
CVE-2026-84779: Subscriber Broken Access Control in Agentimus – AI SEO, llms.txt & MCP for AI Agents <= 1.51.0 versions.
Subscriber Broken Access Control in Agentimus – AI SEO, llms.txt & MCP for AI Agents
CKAN MCP Server: Cache-key canonicalization collision enables cache confusion / poisoning
## Summary The response cache derives its key from an ambiguous string serialization of the request parameters. `canonicalizeParams` joins sorted `${key}=${value}` pairs with `&` and does not escape...
CKAN MCP Server: Information disclosure via verbose error reflection
## Summary Error paths reflect raw upstream response bodies and internal exception messages back to the caller instead of a sanitized, generic message. When the server is pointed at (or redirected/SS...
HiddenLayer Raises $100 Million for AI Runtime Security
The Austin-based company will invest in agentic runtime security capabilities to secure AI coding agents. The post HiddenLayer Raises $100 Million for AI Runtime Security appeared first on SecurityWee...
AI Agent Firewall Startup AIR Security Emerges From Stealth With $50 Million
The startup’s firewall evaluates AI skills, plugins and MCP servers for malicious instructions, excessive permissions and software supply chain risks. The post AI Agent Firewall Startup AIR Security E...
CVE-2026-84887: A vulnerability was identified in simular-ai Agent-S up to 0.3.2. Affected by this issue is some unknown functionality o
A vulnerability was identified in simular-ai Agent-S up to 0.3.2. Affected by this issue is some unknown functionality of the file grounding.py of the component Model-generated GUI Action Execution Wo...