AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories

LLM agents complete tasks by issuing sequences of tool calls, and every observation they read is a channel through which an indirect prompt injection can enter. A successful injection has a characteristic shape when the trajectory is read in order: a benign prefix gives way to actions that serve...

firefox-devtools-mcp v0.10.2

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...

SUSE CVE-2026-73506

Oh My Posh is the most customisable and low-latency cross platform/shell prompt renderer. Prior to 29.35.1, writes rune in src/terminal/writer.go emitted attacker-controlled current directory names and Git metadata, including Commit.Subject, Commit.Author.Name, Commit.Author.Email, and...

PT-2026-105771

The /v1/chat/agents/agent id/edit endpoint in local-operator versions before 0.47.5 resolves the caller-supplied file path with expanduser.resolve and reads it without checking that it lies inside the agent's workspace. An unauthenticated client with network access to the API can supply an absolu...

EUVD-2026-58064

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

GHSA-PR7F-P5MW-FC87 vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

Executive Summary The 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...

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

Executive Summary The 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...

GHSA-M4RF-3FR8-XWX3 vulnerabilities

Vulnerabilities for packages: nemo, open-webui...

How to secure edge AI in customer-owned environments

In this article 1. Edge AI changes the trust model for AI systems 2. Constrain model actions through deterministic mediation 3. Establish trust before releasing sensitive assets 4. Verify runtime before releasing sensitive assets 5. Verify artifacts that shape model behavior 6. Next steps Edge AI...

How to secure edge AI in customer-owned environments

In this article 1. Edge AI changes the trust model for AI systems 2. Constrain model actions through deterministic mediation 3. Establish trust before releasing sensitive assets 4. Verify runtime before releasing sensitive assets 5. Verify artifacts that shape model behavior 6. Next steps Edge AI...

EUVD-2026-60965

CodeWhale: rlmeval auto-approves arbitrary Python execution, bypassing the user's approval policy RCE...

CodeWhale: rlm_eval auto-approves arbitrary Python execution, bypassing the user's approval policy (RCE)

Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 57f3c89471e27ac4032d9791f6885e5d4408c381. Users should upgrade to 0.8.64 or later. The original reporter analysis is...

EUVD-2026-60971

CodeWhale: Argument Injection in gitshow Tool Allows Arbitrary File Write Without Approval...

CodeWhale: exec_shell_interact sends LLM-controlled input to a running shell without an approval prompt (privilege escalation)

Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 57f3c89471e27ac4032d9791f6885e5d4408c381. Users should upgrade to 0.8.64 or later. The original reporter analysis is...

GHSA-G29H-PFMP-QP9R CodeWhale: exec_shell_interact sends LLM-controlled input to a running shell without an approval prompt (privilege escalation)

Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 57f3c89471e27ac4032d9791f6885e5d4408c381. Users should upgrade to 0.8.64 or later. The original reporter analysis is...

NPM: CodeWhale: Project config `instructions` override enables arbitrary file read into AI system prompt via cloned repository

NPM: CodeWhale: Project config instructions override enables arbitrary file read into AI system prompt via cloned repository vulnerability discovered by ? in WordPress Npm deepseek-tui versions = 0.8.8, 0.8.41...

GHSA-62F5-CP2P-VQ95 CodeWhale: Project config `instructions` override enables arbitrary file read into AI system prompt via cloned repository

Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 43563356b98c6b993085554da82e77370160a31c. Users should upgrade to 0.8.64 or later. The original reporter analysis is...

NPM: CodeWhale: Project config `instructions` override enables arbitrary file read into AI system prompt via cloned repository

NPM: CodeWhale: Project config instructions override enables arbitrary file read into AI system prompt via cloned repository vulnerability discovered by ? in WordPress Npm codewhale versions = 0.8.41, 0.8.64...

EUVD-2026-60966

CodeWhale: Project config instructions override enables arbitrary file read into AI system prompt via cloned repository...

CodeWhale: Project config `instructions` override enables arbitrary file read into AI system prompt via cloned repository

Maintainer resolution The CodeWhale maintainers validated this report. The affected package ranges are recorded in the advisory metadata. Version 0.8.64 contains the fix in commit 43563356b98c6b993085554da82e77370160a31c. Users should upgrade to 0.8.64 or later. The original reporter analysis is...