5421 matches found
CVE-2026-82280
Quivr through 0.0.322 fails to validate ownership in prompt endpoints, allowing authenticated users to modify any prompt by identifier. Attackers with read-only access to shared brains can read exposed prompt identifiers and overwrite system prompts affecting all brain users...
CVE-2026-82233
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 Agent to upload sensitive files such as SSH keys or credentials from outside the workspace into t...
CVE-2026-82233 SiYuan before v3.8.1 Path Traversal via asset.upload
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 Agent to upload sensitive files such as SSH keys or credentials from outside the workspace into t...
CVE-2026-82233
SiYuan before v3.8.1 is affected by a path traversal vulnerability in the asset.upload MCP tool , which accepts arbitrary absolute file paths without workspace boundary validation. An attacker can leverage prompt injection to induce the AI Agent to upload sensitive files—such as SSH keys or crede...
EUVD-2026-67685
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 Agent to upload sensitive files such as SSH keys or credentials from outside the workspace into t...
CVE-2026-82233 SiYuan before v3.8.1 Path Traversal via asset.upload
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 Agent to upload sensitive files such as SSH keys or credentials from outside the workspace into t...
CVE-2026-82233
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 Agent to upload sensitive files such as SSH keys or credentials from outside the workspace into t...
CVE-2026-82233 SiYuan before v3.8.1 Path Traversal via asset.upload
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 Agent to upload sensitive files such as SSH keys or credentials from outside the workspace into t...
PT-2026-83303
Quivr through 0.0.322 fails to validate ownership in prompt endpoints, allowing authenticated users to modify any prompt by identifier. Attackers with read-only access to shared brains can read exposed prompt identifiers and overwrite system prompts affecting all brain users...
CVE-2026-82233: Improper Limitation of a Pathname to a Restricted Directory
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 Agent to upload sensitive files such as SSH keys or credentials from outside the workspace into t...
CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?
Prompt injection attacks on Large Language Model LLM agents seek to introduce malicious instructions or content into external text sources retrieved by agents, forcing the underlying LLMs to execute harmful actions outside their benign scope. While current defenses effectively counter known...
CVE-2026-82280: Authorization Bypass Through User-Controlled Key
Quivr through 0.0.322 fails to validate ownership in prompt endpoints, allowing authenticated users to modify any prompt by identifier. Attackers with read-only access to shared brains can read exposed prompt identifiers and overwrite system prompts affecting all brain users...
LongPIBench: A Long-Context Benchmark for Prompt Injection
Prompt injection attacks pose a serious security risk to large language models in real-world applications. However, existing prompt injection benchmarks primarily focus on short-context inputs, leaving the attacks and defenses in long-context settings largely unexplored. This gap leads to a...
PT-2026-83085
Name of the Vulnerable Software and Affected Versions SiYuan versions prior to 3.8.1 Description A path traversal issue exists in the asset.upload MCP tool, which allows the use of arbitrary absolute file paths because it lacks workspace boundary validation. Through prompt injection, an attacker...
CVE-2026-37003
Agno up to and including 2.5.8 is vulnerable to Remote Code Execution RCE via prompt injection. The PythonTools and ShellTools components pass unsanitized, LLM-generated arguments directly to execution sinks including exec, runpy.runpath, and subprocess.run. An unauthenticated attacker can exploi...
Inside 90 days of attacks on AI infrastructure
Wiz honeypots uncover active campaigns targeting LiteLLM, MCP servers, and AI frameworks through RCE, blind prompt injection, and memory credential theft...
Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers
Cybersecurity researchers have disclosed details of a vulnerability in Amazon Kiro, an artificial intelligence AI-powered, agentic integrated development environment IDE, that could facilitate data exfiltration via prompt injection and Kiro Powers. The security flaw, which does not have a CVE...
CVE-2026-71492
A flaw was found in Banks. The DirectoryPromptRegistry.set function improperly handles attacker-controlled Prompt.name and Prompt.version values. This allows for path traversal, enabling an attacker to write arbitrary files outside the intended registry root. This vulnerability could lead to...
SkillSpector v2.10.0
SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills used by Claude Code, Codex CLI, Gemini CLI, etc. execute with implicit trust and minimal vetting. Research shows that 26.1% of...
