(A)I Sees What You Don't: Exploiting New Attack Surfaces in Third-Party Mobile Agents

Third-party mobile agents powered by Vision-Language Models VLMs have emerged as a promising paradigm for automating smartphone interactions. These agents act as high-privilege decision-makers, perceiving device states through screenshots and executing actions via VLM reasoning, transforming how ...

PraisonAI `deploy --type api` emits a Flask server with authentication disabled by default

SummaryCVE-2026-44338 GHSA-6rmh-7xcm-cpxj documents that PraisonAI ships a code-generator praisonai.deploy.api.generateapiservercode that emits a Flask API server with authentication disabled by default. Users who follow the documented quickstart praisonai deploy --type api get a server that:-...

PYSEC-2026-465 PraisonAI `deploy --type api` emits a Flask server with authentication disabled by default

Summary CVE-2026-44338 GHSA-6rmh-7xcm-cpxj documents that PraisonAI ships a code-generator praisonai.deploy.api.generateapiservercode that emits a Flask API server with authentication disabled by default. Users who follow the documented quickstart praisonai deploy --type api get a server that: -...

PYSEC-2026-466 PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset

Summary PraisonAI's call server exposes a network-facing agent control API without authentication when CALLSERVERTOKEN is not configured. The affected component is the praisonai.api.agentinvoke router as mounted by praisonai.api.call. The authentication helper verifytoken fails open when...

PraisonAI has sandbox escape via exception frame traversal in `execute_code` (subprocess mode)

Summaryexecutecode in praisonaiagents.tools.pythontools defaults tosandboxmode="sandbox", which runs user code in a subprocess wrapped with arestricted builtins dict and an AST-based blocklist. The AST blocklist embedded inside the subprocess wrapper blockedattrs, line 143 ofpythontools.py contai...

PraisonAI Has Missing Authentication in WebSocket Gateway

SummaryThe PraisonAI Gateway server accepts WebSocket connections at /ws and serves agent topology at /info with no authentication. Any network client can connect, enumerate registered agents, and send arbitrary messages to agents and their tool sets. Detailsgateway/server.py:242 source -...

Cybersecurity AI (CAI) vulnerable to Command Injection in run_ssh_command_with_credentials Agent tool

SummaryA command injection vulnerability is present in the function tool runsshcommandwithcredentials available to AI agents. Details This is the source code of the function tool runsshcommandwithcredentials code: python@functiontooldef runsshcommandwithcredentials host: str, username: str,...

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...

Maestro 0.17.2

Maestro is a cross-platform desktop app for orchestrating your fleet of AI agents and projects. It's a high-velocity solution for hackers who are juggling multiple projects in parallel. Designed for power users who live on the keyboard and rarely touch the mouse. Collaborate with AI to create...

IronCurtain 0.12.0

IronCurtain is an early-stage research project exploring how to make AI agents safe enough to be genuinely useful. It is a runtime for autonomous AI agents, where security policy is derived from a human-readable constitution. APIs, configuration formats, and architecture may change...

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...

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...

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 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-2026-4339

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-2026-9699 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...

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...