5425 matches found
Structured but Fragile: On the Limits of LLMs in Cybersecurity Decision-Making
Large language models LLMs are increasingly used in cybersecurity workflows, yet it remains unclear whether they can perform structured security reasoning or merely rely on superficial cues and prior knowledge. We study this question in the context of defence selection over attack graphs derived...
Vibe Coding and Web Application Security: A Twin-Prompt Study
Large language models increasingly generate complete web applications from natural-language prompts, raising the question of whether explicitly requesting security best practice improves the result. We study six functionally distinct web applications, each generated in two prompt variants that ar...
TraceGrant: A Contract-Governed Security Framework for the Task-Effect Lifecycle of Networked LLM Agents
Networked large language model LLM agents retrieve information from email, cloud storage, calendars, transaction platforms, and Web services to complete multistep tasks that produce persistent external effects. The same content needed for legitimate execution may also contain indirect prompt...
CVE-2026-62676: Incomplete List of Disallowed Inputs
Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, the shared shell-command parser in omnigent/policies/builtins/shell.py fails to recognize combined interpreter flags, the timeout, nice, setsid, and stdbuf wrappers, command...
PT-2026-79457
Name of the Vulnerable Software and Affected Versions Xinference versions prior to 2.7.0 Description Xinference passes attacker-influenced Llama3 tool-call output to the eval function within xinference/model/llm/tool parsers/llama3 tool parser.py and xinference/model/llm/utils.py. Requests sent t...
SecureAI-Scan v0.10.0
SecureAI-Scan The AI security scanner that proves its findings. SecureAI-Scan finds LLM, MCP, Agent Skill, and RAG vulnerabilities in TypeScript, JavaScript, and Python — and shows you the evidence: the exact source → flow → sink path for every dataflow finding, resolved through real imports, not...
agent-scan v0.6.0
Snyk Agent Scan Discover and scan agent components on your machine for prompt injections and vulnerabilities including agents, MCP servers, skills. Note: CLI output is experimental and subject to change Agent Scan v0.5.x planned for deprecation The raw output of this CLI — including issue codes,...
EUVD-2026-63135
Agno's PythonTools in libs/agno/agno/tools/python.py contains a path traversal vulnerability that allows attackers to read, write, or execute arbitrary files by supplying parent-directory traversal sequences in the filename argument passed to readfile, savetofile, or runpythonfile tool actions...
CVE-2026-76832 Agno PythonTools Path Traversal via joinpath file_name argument
Agno's PythonTools in libs/agno/agno/tools/python.py contains a path traversal vulnerability that allows attackers to read, write, or execute arbitrary files by supplying parent-directory traversal sequences in the filename argument passed to readfile, savetofile, or runpythonfile tool actions...
CVE-2026-54689
creationtimestamp| type| source ---|---|--- 2026-08-19 20:35:08+00:00| published-proof-of-concept| https://github.com/ihor-sokoliuk/mcp-searxng/security/advisories/GHSA-wppf-h75h-6pm6...
GHSA-RR55-JP92-8WP2 claude-faf-mcp has an arbitrary local file read/write via unconfined `path` argument in FAF tools
Summary claude-faf-mcp MCP tools accept a caller-controlled path argument and resolve it expansion + path.resolve straight into a filesystem read/write without confining it to a trusted project directory. An absolute path or ../ traversal is resolved and used as-is, so the server process can be...
faf-mcp has an arbitrary local file read/write via unconfined `path` argument in FAF tools
Summary faf-mcp MCP tools accept a caller-controlled path argument and resolve it expansion + path.resolve straight into a filesystem read/write without confining it to a trusted project directory. An absolute path or ../ traversal is resolved and used as-is, so the server process can be made to...
GHSA-CC2G-GQ8C-R332 grok-faf-mcp has an arbitrary local file read via unconfined `path` argument in FAF tools
Summary Several grok-faf-mcp MCP tools accept a caller-controlled path argument and resolve it expansion + path.resolve straight into a filesystem read without confining it to a trusted project directory. An absolute path or ../ traversal is resolved and used as-is, so the server process can be...
WordPress Contest Gallery plugin < 30.0.7 - Subscriber+ OpenAI Prompt History Disclosure via post_cg_get_openai_prompts vulnerability
Subscriber+ OpenAI Prompt History Disclosure via postcggetopenaiprompts vulnerability discovered by Meher Sudhakar Abbireddi in WordPress Plugin Contest Gallery versions 30.0.7...
PYSEC-2026-3704 vLLM: Completion prompt lists fan out into unbounded engine requests
Summary The /v1/completions request model accepts prompt as a list of text prompts or a list of token-id prompts without any outer prompt-count bound. The serving path turns each element into a separate engine input, creates one engine generator per element, merges all generators, and allocates a...
mcp-atlassian: Arbitrary file read via missing path validation in confluence_upload_attachment
Summaryconfluenceuploadattachment passes filepath directly to openfilepath, "rb" with no path validation. Any authenticated MCP client — or an AI agent manipulated via prompt injection — can read any file the server process can access and exfiltrate it to Confluence as an attachment. DetailsRoot...
PYSEC-2026-3683 mcp-atlassian: Arbitrary file read via missing path validation in confluence_upload_attachment
Summary confluenceuploadattachment passes filepath directly to openfilepath, "rb" with no path validation. Any authenticated MCP client — or an AI agent manipulated via prompt injection — can read any file the server process can access and exfiltrate it to Confluence as an attachment. Details Roo...
firefox-devtools-mcp v0.10.0
Firefox DevTools MCP Model Context Protocol server for automating Firefox via WebDriver BiDi through Selenium WebDriver. Works with Claude Code, Claude Desktop, Cursor, Cline and other MCP clients. Repository: https://github.com/mozilla/firefox-devtools-mcp Note : This MCP server requires a local...
When Agents Go Rogue: The OpenClaw Supply Chain Crisis
When Agents Go Rogue: The OpenClaw Supply Chain Crisis By Aniket Choukde, Vikas Mishra and Yadunadh · August 19, 2026 This blog was also written by Akhil Reddy and Pavan Kumar Podila Executive Summary The cybersecurity landscape is currently undergoing a seismic shift driven by the adoption of...
PT-2026-78837
Name of the Vulnerable Software and Affected Versions Agno affected versions not specified Description PythonTools in libs/agno/agno/tools/python.py contains a path traversal issue. This occurs when parent-directory traversal sequences are supplied in the file name argument passed to the read fil...