PT-2026-97402

Plex Media Server before 1.43.3.10861 builds a file path from the url parameter without checking it for ../ sequences, allowing path traversal via '/system/agents/media/get'. A remote attacker with a valid session token could read any file that the target user can access. This access includes the...

CVE-2026-93529: Missing Authorization

Contributor Broken Access Control in WSP MCP – AI Agents Connector = 2.7.0 versions...

Malicious code in ubiquiti-agents-link-mcp (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 8827e987697ea6ef619055c53ae1654800a838c18419ffc8a09e872c6f16adc4 The package's bin entry index.js runs execSync'id' and collects os.userInfo.username and os.hostname, then HTTPS-POSTs the JSON payload to the...

MAL-2026-16409 Malicious code in ubiquiti-agents-link-mcp (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 8827e987697ea6ef619055c53ae1654800a838c18419ffc8a09e872c6f16adc4 The package's bin entry index.js runs execSync'id' and collects os.userInfo.username and os.hostname, then HTTPS-POSTs the JSON payload to the...

aquaman v0.15.0

🔱 Aquaman 🔱 The only independent credential proxy for AI agents: bring-your-own-vault isolation & least-privilege request policies. Your keys stay where you already keep them, never in the agent's memory. Compatible with 1Password, keychain, keepassxc and many others. You set up Claude Code, Code...

ironcurtain memory-mcp-server/v0.2.1

IronCurtain A secure runtime for autonomous AI agents, where security policy is derived from a human-readable constitution. When someone writes "secure," you should immediately be skeptical.What do we mean by secure? !WARNING Research Prototype. IronCurtain is an early-stage research project...

CVE-2026-80110

A flaw was found in pki-core. The v2 REST ACL filter selects a tie-breaking permission for colliding literal and wildcard ACL keys using lexicographic string comparison rather than specificity, causing a wildcard-mapped permission to override a more specific literal-mapped permission when both...

runeward

AIエージェントのためのオープンソース・ガバナンス・ハーネス。 あらゆるAIエージェントに対して、強制可能なポリシー、人間による承認、分離された実行環境、予算、そして署名付き証跡を提供します。Runewardは、新しいモデルやオーケストレーションスタックを必要とせず、既存のエージェントやマルチエージェントフレームワークと連携して動作します。 1つのコマンドで証明する 前提条件: 稼働中のDocker/Podmanエンジンとrunewardバイナリ。 root@kitploit: runeward quickstart...

node9-proxy v2.16.2

🛡️ node9 Access control for AI agents Your AI agents can reach Slack, GitHub, email, and your database. node9 decides what they may do with each one. Credential jail · secrets and PII · destructive git, SQL and shell held for review · MCP tool pinning · network egress allowlist · loop breaker · on...

VulnCheck KEV: CVE-2026-88062

OmniRoute is an open-source AI gateway providing a single endpoint for multiple model providers. In 3.8.49 and earlier, the OmniRoute POST /api/acp/agents custom ACP agent endpoint accepted attacker-controlled binary and versionCommand values and used only a self-consistency check before...

kontext-cli v1.8.1

Website | Documentation | Dashboard | Discord Stop risky AI-agent actions before they run AI agents do more than suggest code. They run shell commands, read files, call services, change infrastructure, and interact with production systems. Kontext puts local policy between AI agents and the tools...

CVE-2026-18911

ManageEngine DataSecurity Plus versions before 6310 are vulnerable to an agent authentication bypass, allowing unenrolled agents to send requests without proper authentication...

EUVD-2026-82655

ManageEngine DataSecurity Plus versions before 6310 are vulnerable to an agent authentication bypass, allowing unenrolled agents to send requests without proper authentication...

CVE-2026-18911

ManageEngine DataSecurity Plus versions before 6310 are vulnerable to an agent authentication bypass, allowing unenrolled agents to send requests without proper authentication...

CVE-2026-18911

ManageEngine DataSecurity Plus versions before 6310 are vulnerable to an agent authentication bypass, allowing unenrolled agents to send requests without proper authentication...

CVE-2026-18911

ManageEngine DataSecurity Plus versions prior to 6310 are affected by an agent authentication bypass that allows unenrolled agents to send requests to the product without proper authentication. The vulnerability is scored CVSS 7.5 (High) with a network attack vector, high attack complexity, no re...

screenpipe app-v2.7.42

DOWNLOAD SCREENPIPE screenpipe | YC S26 Screenpipe finds work worth automating in your company Continuously record your company's computer work, map workflows, help find work worth automating, and power agents' context https://github.com/user-attachments/assets/70fe94eb-6d2a-47ca-b7c3-c8ead13a5b7...

CVE-2026-18911: Improper Input Validation

ManageEngine DataSecurity Plus versions before 6310 are vulnerable to an agent authentication bypass, allowing unenrolled agents to send requests without proper authentication...

kin v0.7.20

A new foundation for code. Kin is a graph-native code repository for people and AI agents. It stores source, recorded code relationships, and versioned history as repository state. The graph is the repository model, not a search index maintained beside another repository. Functions, types, and th...

MAL-2026-16250 Malicious code in marketing-mcp (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 87216e00fe68e2de8b140f1f9ffc2db5a8e814f38030e2eb6120c9ae9e7ca3ff The package exposes an MCP tool sendpath that reads a caller-specified local file and POSTs its contents to a hardcoded...