Agentic / MCP
653 entries
Every Agentic / MCP entry VulnWatch has indexed, sorted by publication date.
Subscribe to this tag's RSS feed
CVE-2026-84886: A vulnerability was determined in simular-ai Agent-S up to 0.3.2. Affected by this vulnerability is the function ImageDa
A vulnerability was determined in simular-ai Agent-S up to 0.3.2. Affected by this vulnerability is the function ImageData of the file gui_agents/s1/utils/ocr_server.py of the component OCR HTTP API....
CVE-2026-84885: A vulnerability has been found in simular-ai Agent-S 0.3.1/0.3.2. This impacts an unknown function of the file code_agen
A vulnerability has been found in simular-ai Agent-S 0.3.1/0.3.2. This impacts an unknown function of the file code_agent.py of the component CodeAgent. Such manipulation leads to denial of service. T...
Omnigent: Shared Agent Bundle Overwrite Leads to Authenticated Runner RCE
### Summary An authenticated user with edit access to their own session can overwrite a shared/template agent by uploading a full agent bundle through `PUT /sessions/{session_id}/agent`. Shared/temp...
OpenLeash Adds a Human Check to Risky AI Agent Actions
The security tool intercepts potentially dangerous agent actions, blocking clear threats and requesting human approval when intent is uncertain. The post OpenLeash Adds a Human Check to Risky AI Agent...
CKAN MCP Server: MQA server allowlist bypass via unanchored regex (`isValidMqaServer`)
## Summary The `ckan_get_mqa_quality` and `ckan_get_mqa_quality_details` tools restrict their `server_url` argument to `dati.gov.it` via a regular expression. The regex is anchored only at the start...
Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
Manifold Security has disclosed eight security flaws across seven command-line AI coding agents in which a repository's own Git configuration names a command that the agent runs on the developer's mac...
Palo Alto Networks Acquires AI Agent Platform Console
The cybersecurity giant announced the acquisition alongside quarterly results showing a 34% increase in revenue and strong growth in next-generation security ARR. The post Palo Alto Networks Acquires...
Sevii Targets AI-Speed Attacks With Preemptive Autonomous Defense
Sevii has expanded its ADR platform with AI agents designed to investigate, contain, and remediate AI-driven attacks within minutes. The post Sevii Targets AI-Speed Attacks With Preemptive Autonomous...
CVE-2026-19591: OpenAI Codex CLI for Windows, macOS, and Linux and Codex Desktop for Windows and macOS misclassified certain PowerShell
OpenAI Codex CLI for Windows, macOS, and Linux and Codex Desktop for Windows and macOS misclassified certain PowerShell commands as safe because their command-safety parser interpreted PowerShell's st...
Attackers Steal METR API Key and Consume AI Credits Worth About $600,000
METR (short for Model Evaluation and Threat Research and pronounced "Meter"), a research non-profit that evaluates frontier artificial intelligence (AI) models for their ability to carry out long-hori...
CVE-2026-79750: MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate end
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.30, MCPHub scopes...
CVE-2026-79749: MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate end
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.32, MCPHub's SSRF...
CVE-2026-79748: MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate end
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 0.12.15, the POST /api...
CVE-2026-79747: MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate end
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.32, an authenticat...
CVE-2026-79746: MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate end
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.31, when a bearer...
CVE-2026-79745: MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate end
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.32, the built-in p...
CVE-2026-79744: MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate end
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 1.0.29, MCPHub's PUT /...
CVE-2026-79743: MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate end
MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies. Prior to version 0.12.13, MCPB File Upl...
⚡ Weekly Recap: Chinese Spy Proxy, AI Agents Go Off-Task, Router Backdoors and More
The boring parts caused most of the trouble. A router shipped ready to listen. A fake check turned the user into the installer. Trusted systems collected traffic and passwords, then cleaned the logs....
What the Hugging Face Incident Teaches Security Leaders About AI Agent Access
Security teams must treat autonomous agents as highly privileged identities. The post What the Hugging Face Incident Teaches Security Leaders About AI Agent Access appeared first on SecurityWeek.
CVE-2026-81315: Origin Validation Error vulnerability in ash-project ash_ai allows a malicious web page to bypass the MCP server's DNS-r
Origin Validation Error vulnerability in ash-project ash_ai allows a malicious web page to bypass the MCP server's DNS-rebinding protection and issue cross-site requests to a user's local MCP server w...
CVE-2026-54746: Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale. From 0.40.0 until 0
Hatchet is a platform for orchestrating background tasks, AI agents, and durable workflows at scale. From 0.40.0 until 0.91.1, the Dispatcher gRPC service does not verify that a request's worker ID be...
CVE-2026-82233: SiYuan before v3.8.1 contains a path traversal vulnerability in the asset.upload MCP tool that accepts arbitrary absolut
SiYuan before v3.8.1 contains a path traversal vulnerability in the asset.upload MCP tool that accepts arbitrary absolute file paths without workspace boundary validation. Attackers can induce the AI...
Nearly 700 rogue AI agents coordinated in the Hugging Face attack
New details about the July attack on Hugging Face reveal that hundreds of AI agents driven by OpenAI's internal IM1 model coordinated the compromise through an unauthorized message board. [...]
CVE-2026-37006: A vulnerability in the WebSocket endpoint of gpt-researcher v0.14.7 and before allows an unauthenticated remote attacker
A vulnerability in the WebSocket endpoint of gpt-researcher v0.14.7 and before allows an unauthenticated remote attacker to achieve code execution via malicious Model Context Protocol configurations.