vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

Executive SummaryThe follow-up protection for CVE-2025-62164 is incomplete at vLLM revision 26587f9519e22a5c4549ead7595ad9ca3229c4fd. It wraps serialized prompt-embedding reconstruction and dense conversion in torch.sparse.checksparsetensorinvariants, but PyTorch 2.11.0 implements that context wi...

PYSEC-2026-3810 Banks: Path traversal in `DirectoryPromptRegistry.set()` allows arbitrary file write outside the registry root

Summary DirectoryPromptRegistry.set interpolates the attacker-controllable Prompt.name into a Path expression with no canonicalization. An application that derives the prompt name from request data lets a caller write attacker-controlled bytes outside the configured registry directory. Details...

PYSEC-2026-3892 PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server

Summary The PraisonAI MCP server exposes an HTTP-stream transport praisonai mcp serve --transport http-stream that binds to localhost and, by default, has no API key. Its only access control for browser-originated requests is an Origin allowlist, which the code implements as required by the MCP...

PYSEC-2026-3880 OpenHarness remote project-context commands allow persistent prompt poisoning

OpenHarness /issue and /prcomments slash commands lack remoteinvocable=False protection, allowing remote channel senders to write attacker-controlled Markdown into project context files. Admitted remote attackers can inject malicious content into .openharness/issue.md and .openharness/prcomments....

OpenHarness remote project-context commands allow persistent prompt poisoning

OpenHarness /issue and /prcomments slash commands lack remoteinvocable=False protection, allowing remote channel senders to write attacker-controlled Markdown into project context files. Admitted remote attackers can inject malicious content into .openharness/issue.md and .openharness/prcomments....

Flowise CSV Agent Prompt Injection Remote Code Execution Vulnerability

This vulnerability allows remote attackers to execute arbitrary code on affected installations of Flowise. Authentication is not required to exploit this vulnerability. The specific flaw exists within the run method of the CSVAgents class. The issue results from insufficient input sanitization wh...

Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation

The integration of Large Language Models LLMs into Security Operations Centers SOCs streamlines threat intelligence but introduces critical vulnerabilities, notably indirect prompt injection via log poisoning. Adversaries exploit this vector to execute multistep "promptware'' kill chains by...

No-Box Vulnerability Analysis: Description-Only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers

Conventional vulnerability analysis relies on either system access or dynamic interaction, all of which may be unavailable to third-party analysts auditing closed-source, remotely hosted, critical in situ systems, or commercially gated software. Therefore, we propose a new paradigm of no-box...

DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents

When an indirect prompt injection succeeds against an LLM agent, the compromise is visible in the agent's own behavior: a benign prefix of tool calls, a poisoned observation, and a suffix of actions that serve the attacker. An operator needs three facts: where the attack entered, which steps it...

SkillSpector v2.11.1

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. In the 31,132-skill analyzed...

ChatGPT Flaw Let a Planted Prompt Send a Victim's Gmail Data to Another Account

Check Point Research said in a report published today that a single instruction planted in a ChatGPT conversation could cause ChatGPT to quietly work for an attacker while answering the user's question as usual. In the company's proof of concept, that hidden work read data from the user's connect...

Stealing AI Reasoning Traces

Interesting research: "Stealing Reasoning Traces from Proprietary LLM APIs": Abstract: Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather than storing these traces...

PT-2026-87136

A malicious webpage could repeatedly trigger external URL schemes, causing system prompts or external application launches. This could make Firefox for iOS temporarily unusable until the page is closed. This vulnerability was fixed in Firefox for iOS 155.1...

CVE-2026-82584

Improper Neutralization of Escape, Meta, or Control Sequences vulnerability in ash-project igniter allows a malicious package publisher to forge the mix igniter.install confirmation prompt. mix igniter.install prints a confirmation panel an anti-typosquatting safeguard listing a package's hex...

CVE-2026-82584

ash-project igniter (an Elixir build tool) is vulnerable to terminal escape sequence injection in its mix igniter.install confirmation panel. The panel builder in Igniter.Project.Deps wrote publisher-controlled fields (meta.description, owner usernames, requirement names, version) to the terminal...

CVE-2026-82584 Terminal escape sequence injection in the mix igniter.install confirmation prompt via package metadata

Improper Neutralization of Escape, Meta, or Control Sequences vulnerability in ash-project igniter allows a malicious package publisher to forge the mix igniter.install confirmation prompt. mix igniter.install prints a confirmation panel an anti-typosquatting safeguard listing a package's hex...

CVE-2026-82584 Terminal escape sequence injection in the mix igniter.install confirmation prompt via package metadata

Improper Neutralization of Escape, Meta, or Control Sequences vulnerability in ash-project igniter allows a malicious package publisher to forge the mix igniter.install confirmation prompt. mix igniter.install prints a confirmation panel an anti-typosquatting safeguard listing a package's hex...

EEF-CVE-2026-82584 Terminal escape sequence injection in the mix igniter.install confirmation prompt via package metadata

Summary Improper Neutralization of Escape, Meta, or Control Sequences vulnerability in ash-project igniter allows a malicious package publisher to forge the mix igniter.install confirmation prompt. mix igniter.install prints a confirmation panel an anti-typosquatting safeguard listing a package's...

EUVD-2026-72554

Improper Neutralization of Escape, Meta, or Control Sequences vulnerability in ash-project igniter allows a malicious package publisher to forge the mix igniter.install confirmation prompt. mix igniter.install prints a confirmation panel an anti-typosquatting safeguard listing a package's hex...

CVE-2026-82584 Terminal escape sequence injection in the mix igniter.install confirmation prompt via package metadata

Improper Neutralization of Escape, Meta, or Control Sequences vulnerability in ash-project igniter allows a malicious package publisher to forge the mix igniter.install confirmation prompt. mix igniter.install prints a confirmation panel an anti-typosquatting safeguard listing a package's hex...