BadSkill: Backdoor Attacks on Agent Skills Via Model-In-Skill Poisoning

Agent ecosystems increasingly rely on installable skills to extend functionality, and some skills bundle learned model artifacts as part of their execution logic. This creates a supply-chain risk that is not captured by prompt injection or ordinary plugin misuse: a third-party skill may appear...

CLEANSTART-2026-FZ55932 SSH clients receiving SSH_AGENT_SUCCESS when expecting a typed response will panic and cause early termination of the client process

Multiple security vulnerabilities affect the istio-fips package. SSH clients receiving SSHAGENTSUCCESS when expecting a typed response will panic and cause early termination of the client process. See references for individual vulnerability details...

bsv-sdk ARC broadcaster treats INVALID/MALFORMED/ORPHAN responses as successful broadcasts

ARC broadcaster treats failure statuses as successful broadcasts Summary BSV::Network::ARC's failure detection only recognises REJECTED and DOUBLESPENDATTEMPTED. ARC responses with txStatus values of INVALID, MALFORMED, MINEDINSTALEBLOCK, or any ORPHAN-containing extraInfo / txStatus are silently...

EUVD-2026-20099

The Whole Enquiry Cart for WooCommerce plugin for WordPress is vulnerable to Stored Cross-Site Scripting via the ‘woowholesuccessmsg’ parameter in all versions up to, and including, 1.2.1 due to insufficient input sanitization and output escaping. This makes it possible for authenticated attacker...

PT-2026-31091

Name of the Vulnerable Software and Affected Versions The Whole Enquiry Cart for WooCommerce plugin for WordPress versions up to and including 1.2.1 Description The Whole Enquiry Cart for WooCommerce plugin for WordPress is susceptible to Stored Cross-Site Scripting through the woowhole success m...

WordPress plugin Whole Enquiry Cart for WooCommerce 跨站脚本漏洞

WordPress and WordPress plugins are both products of the WordPress Foundation. WordPress is a blog platform developed using the PHP language. This platform allows users to create personal blogs on servers based on PHP and MySQL. Woocommerce is one of the e-commerce plugins. WP Fastest Cache is a...

CVE-2026-23306 scsi: pm8001: Fix use-after-free in pm8001_queue_command()

In the Linux kernel, the following vulnerability has been resolved: scsi: pm8001: Fix use-after-free in pm8001queuecommand Commit e29c47fe8946 "scsi: pm8001: Simplify pm8001taskexec" refactors pm8001queuecommand, however it introduces a potential cause of a double free scenario when it changes th...

The vulnerability of the tcp_mtup_probe_success() function in the net/ipv4/tcp_input.c module of the Linux operating system allows a hacker to cause a service failure.

The vulnerability of the tcpmtupprobesuccess function in the net/ipv4/tcpinput.c module of the Linux kernel is related to zero-division errors. Exploiting this vulnerability could allow an attacker to cause a service failure...

golang.org/x/crypto/ssh/agent: golang.org/x/crypto/ssh/agent: SSH client panic due to unexpected SSH_AGENT_SUCCESS

A flaw in golang.org/x/crypto/ssh/agent causes the SSH agent client to panic when a peer responds with the generic SSHAGENTSUCCESS 0x06 message to requests expecting typed replies e.g., List, Sign. The unmarshal layer produces an unexpected message type, which the client code does not handle,...

golang.org/x/crypto/ssh/agent: golang.org/x/crypto/ssh/agent: SSH client panic due to unexpected SSH_AGENT_SUCCESS

A flaw in golang.org/x/crypto/ssh/agent causes the SSH agent client to panic when a peer responds with the generic SSHAGENTSUCCESS 0x06 message to requests expecting typed replies e.g., List, Sign. The unmarshal layer produces an unexpected message type, which the client code does not handle,...

golang.org/x/crypto/ssh/agent: golang.org/x/crypto/ssh/agent: SSH client panic due to unexpected SSH_AGENT_SUCCESS

A flaw in golang.org/x/crypto/ssh/agent causes the SSH agent client to panic when a peer responds with the generic SSHAGENTSUCCESS 0x06 message to requests expecting typed replies e.g., List, Sign. The unmarshal layer produces an unexpected message type, which the client code does not handle,...

Security Bulletin: Unexpected SSH_AGENT_SUCCESS Response Causes Client Panic and Premature Termination in SSH Client, affects watsonx.data

Summary SH clients receiving SSHAGENTSUCCESS when expecting a typed response will panic and cause early termination of the client process. This can affect watsonx.data. Vulnerability Details CVEID:CVE-2025-47913 DESCRIPTION: SSH clients receiving SSHAGENTSUCCESS when expecting a typed response wi...

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent...

When Scanners Lie: Evaluator Instability in LLM Red-Teaming

Automated LLM vulnerability scanners are increasingly used to assess security risks by measuring different attack type success rates ASR. Yet the validity of these measurements hinges on an often-overlooked component: the evaluator who determines whether an attack has succeeded. In this study, we...

golang.org/x/crypto/ssh/agent: golang.org/x/crypto/ssh/agent: SSH client panic due to unexpected SSH_AGENT_SUCCESS

A flaw in golang.org/x/crypto/ssh/agent causes the SSH agent client to panic when a peer responds with the generic SSHAGENTSUCCESS 0x06 message to requests expecting typed replies e.g., List, Sign. The unmarshal layer produces an unexpected message type, which the client code does not handle,...

Agent Privilege Separation in OpenClaw: A Structural Defense against Prompt Injection

Prompt injection remains one of the most practical attack vectors against LLM-integrated applications. We replicate the Microsoft LLMail-Inject benchmark Greshake et al., 2024 against current generation models running inside OpenClaw, an open source multitool agent platform. Our proposed defense...

Parse Server vulnerable to user enumeration via email verification endpoint

Impact The email verification endpoint /verificationEmailRequest returns distinct error responses depending on whether an email address belongs to an existing user, is already verified, or does not exist. An attacker can send requests with different email addresses and observe the error codes to...

CVE-2026-31830 sigstore-ruby verifier returns success for DSSE bundles with mismatched in-toto subject digest

sigstore-ruby is a pure Ruby implementation of the sigstore verify command from the sigstore/cosign project. Prior to 0.2.3, Sigstore::Verifierverify does not propagate the VerificationFailure returned by verifyintoto when the artifact digest does not match the digest in the in-toto attestation...

IU: Imperceptible Universal Backdoor Attack

Backdoor attacks pose a critical threat to the security of deep neural networks, yet existing efforts on universal backdoors often rely on visually salient patterns, making them easier to detect and less practical at scale. In this work, we introduce a novel imperceptible universal backdoor attac...

AdapTools: Adaptive Tool-Based Indirect Prompt Injection Attacks on Agentic LLMs

The integration of external data services e.g., Model Context Protocol, MCP has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical security vulnerabilities, particularly indirect prompt injection IPI attacks...