PT-2026-53540

The execute command function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell metacharacters. --- Description PraisonAI's workflow system and...

Understanding and Evaluating Claw-Like Agent Security through a Computer-Systems Lens

Claw-like AI agents e.g., OpenClaw are always-on processes with persistent access to credentials, files, tools, and external services. They take on system-level responsibilities -- installing packages, maintaining state, scheduling subtasks, and mediating I/O -- making security failures far more...

Malicious code in livekit-agents (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 5abf921f58c69745fee91e812853b493a282f3d42f55db38516ba54b827ea35b The unscoped npm package livekit-agents advertises itself in README as the official LiveKit Agents SDK and links to livekit.io documentation, but the...

MAL-2026-6555 Malicious code in livekit-agents (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 5abf921f58c69745fee91e812853b493a282f3d42f55db38516ba54b827ea35b The unscoped npm package livekit-agents advertises itself in README as the official LiveKit Agents SDK and links to livekit.io documentation, but the...

Cybersecurity Is the True Frontier for Generative AI Success or Failure

Cybersecurity is a real-life test-bed for many machine learning problems at once, especially when considering modern strides in using Large Language Models LLMs to automate processes as "agents.'' Cybersecurity workflows require orchestrating hundreds of standard and bespoke tools through various...

CVE-2026-4339

Mattermost CPT: CVE-2026-4339 affects Mattermost versions 10.11.x up to 10.11.18, 11.6.x up to 11.6.3, and 11.5.x up to 11.5.6. The vulnerability arises from the Agents plugin MCP server failing to validate attachment URLs against internal/private IP ranges, enabling an attacker with MCP stdio ac...

CVE-2026-4339 SSRF via unvalidated attachment URLs in Mattermost Agents plugin MCP server

Mattermost versions 10.11.x = 10.11.18, 11.6.x = 11.6.3, 11.5.x = 11.5.6 fail to validate attachment URLs against internal or private IP ranges in the Mattermost Agents plugin MCP server which allows an attacker with access to the MCP server in stdio mode to perform server-side request forgery SS...

CVE-2026-9699 Mattermost Agents plugin logs unsanitized OpenAI API keys on authentication errors

Mattermost Plugins versions =11.6 10.18.11 11.3.6 11.6.5.0 fail to sanitize error responses from the OpenAI API before logging, which allows a user with access to server logs or support packets to obtain a valid or partially reconstructable OpenAI API key via inspection of mattermost.log entries...

CVE-2026-9699 Mattermost Agents plugin logs unsanitized OpenAI API keys on authentication errors

Mattermost Plugins versions =11.6 10.18.11 11.3.6 11.6.5.0 fail to sanitize error responses from the OpenAI API before logging, which allows a user with access to server logs or support packets to obtain a valid or partially reconstructable OpenAI API key via inspection of mattermost.log entries...

Guardian Agents: The Next Layer of Identity Governance

AI agents are moving through enterprise environments, inheriting permissions, traversing systems, and executing decisions at machine speed with minimal oversight. The identity infrastructure built to govern human access wasn't designed for autonomous actors, and the gap between what enterprises a...

CVE-2026-4339: Server-Side Request Forgery (SSRF)

Mattermost versions 10.11.x = 10.11.18, 11.6.x = 11.6.3, 11.5.x = 11.5.6 fail to validate attachment URLs against internal or private IP ranges in the Mattermost Agents plugin MCP server which allows an attacker with access to the MCP server in stdio mode to perform server-side request forgery SS...

How Humans, Bots, and Agents Communicate about Vulnerabilities in Pull Requests

Developers may reference vulnerabilities in pull request discussions through both explicit identifiers, such as CVEs or GHSAs, and implicit security-related language e.g., "unauthorized access" or "SQL injection". Prior work has primarily focused on explicit identifiers, potentially overlooking...

Oracle Linux 9 : fence-agents (ELSA-2026-19355)

The remote Oracle Linux 9 host has packages installed that are affected by multiple vulnerabilities as referenced in the ELSA-2026-19355 advisory. - bundled PyJWT: upgrade to v2.13.0 to fix CVE-2026-48526 Resolves: RHEL-182313 - bundled pyasn1: fix CVE-2026-30922 Resolves: RHEL-157202 - bundled...

fence-agents security update

4.10.0-110.3 - bundled PyJWT: upgrade to v2.13.0 to fix CVE-2026-48526 Resolves: RHEL-182313 4.10.0-110.2 - bundled pyasn1: fix CVE-2026-30922 Resolves: RHEL-157202 4.10.0-110.1 - bundled cryptography: replace with dependency to fix CVE-2026-26007 - bundled PyJWT: upgrade to v2.12.1 to fix...

GO-2026-5345 Gryph Agents Payload Filter Fails to Strip Tool Payload for Sensitive Content in github.com/safedep/gryph

Gryph Agents Payload Filter Fails to Strip Tool Payload for Sensitive Content in github.com/safedep/gryph...

GO-2026-5261 Nezha has cross-site GET request that can trigger stored cron commands on a victim's agents in github.com/nezhahq/nezha

Nezha has cross-site GET request that can trigger stored cron commands on a victim's agents in github.com/nezhahq/nezha. NOTE: The source advisory for this report contains additional versions that could not be automatically mapped to standard Go module versions. If this is causing false-positive...

Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems

Increasingly autonomous agentic AI systems pose novel multi-agent risks, such as secret collusion via covert communication channels. The natural defence to these collusion attempts is to monitor plain-text communication, but the efficacy of monitors has been called into doubt by increasingly...

Oracle Linux 9 : fence-agents (ELSA-2026-26206)

The remote Oracle Linux 9 host has packages installed that are affected by a vulnerability as referenced in the ELSA-2026-26206 advisory. - bundled PyJWT: upgrade to v2.13.0 to fix CVE-2026-48526 Resolves: RHEL-182313 - bundled pyasn1: fix CVE-2026-30922 Resolves: RHEL-157202 - bundled...

CVE-2026-53765

Chrome DevTools for agents chrome-devtools-mcp lets your coding agent control and inspect a live Chrome browser. From 0.20.0 until 1.1.0, The chrome-devtools-mcp daemon writes its PID file with fs.writeFileSync to a deterministic runtime path. On typical macOS environments, and on Linux sessions...

CVE-2026-53766

Chrome DevTools for agents chrome-devtools-mcp lets your coding agent control and inspect a live Chrome browser. From 0.24.0 until 1.1.0, McpContext.validatePath enforces workspace roots by checking whether path.resolvefilePath textually falls under one of the configured root paths. path.resolve...