CVE-2026-47419 praisonai-platform: Agent endpoints accept any agent_id without workspace ownership check, cross-workspace read/update/delete IDOR

PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an Insecure Direct Object Reference. The agent CRUD endpoints GET / PATCH / DELETE /workspaces/workspaceid/agents/agentid gate access on requireworkspacememberworkspaceid only, then...

CVE-2026-47419 praisonai-platform: Agent endpoints accept any agent_id without workspace ownership check, cross-workspace read/update/delete IDOR

PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an Insecure Direct Object Reference. The agent CRUD endpoints GET / PATCH / DELETE /workspaces/workspaceid/agents/agentid gate access on requireworkspacememberworkspaceid only, then...

CVE-2026-47419

CVE-2026-47419 concerns PraisonAI Platform where agent endpoints under /workspaces/{workspace_id}/agents/{agent_id} suffer an Insecure Direct Object Reference. The description and connected reports show that endpoints gate access with require_workspace_member(workspace_id) but the AgentService.ge...

CVE-2026-47396

PraisonAI is a multi-agent teams system. Prior to version 4.6.40, 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...

CVE-2026-47391

PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a calculateexpression tool implemented with Python eval. The example also binds to 0.0.0.0. A remote unauthenticated attacker...

CVE-2026-47396 PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset

PraisonAI is a multi-agent teams system. Prior to version 4.6.40, 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...

CVE-2026-47396 PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset

PraisonAI is a multi-agent teams system. Prior to version 4.6.40, 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...

CVE-2026-47396

Plausible vulnerability CVE-2026-47396 affects PraisonAI’s call server. Before version 4.6.40, the network-facing API under praisonai.api.agent_invoke (mounted by praisonai.api.call) authenticates fail-open when CALL_SERVER_TOKEN is not configured, exposing unauthenticated access on 0.0.0.0. Endp...

CVE-2026-47391

PraisonAI’s first-party A2A example exposes an unauthenticated /a2a JSON-RPC surface and registers a calculate(expression) tool implemented via Python eval(), bound to 0.0.0.0. A remote attacker can send message/send to a2a, causing the LLM to invoke the unsafe tool and potentially execute arbitr...

CVE-2026-47391 PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution

PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a calculateexpression tool implemented with Python eval. The example also binds to 0.0.0.0. A remote unauthenticated attacker...

CVE-2026-50271 vulnerabilities

Vulnerabilities for packages: litellm, datadog-agent-fips, datadog-agent...

GHSA-MW54-J2V2-42HR vulnerabilities

Vulnerabilities for packages: litellm, datadog-agent-fips, datadog-agent...

Open-Source Android AI Agents Could Let Invisible Screen Text Run Code on Host PCs

An Android app that can draw over other windows and write to shared storage can slip instructions to the AI agent driving that phone, in text no human eye will ever see. Two more steps, and the same app is running commands on the PC driving the agent. Researchers demonstrated that chain, plus six...

CLEANSTART-2026-XP63957 Security fixes for CVE-2026-42504 applied in versions: 1.76.1-r0

Security vulnerability affects the newrelic-infrastructure-agent package. This issue is resolved in later releases. See references for vulnerability details...

This Week in Spring - July 21st, 2026

Welcome to another installment of This Week in Spring! I'm writing this while enjoying a cup of coffee from the Caribbean on a little PTO. How're you doin'? Whenever I go on PTO, I like to sit by some body of water with a coffee and a laptop nearby. I alternate between plunges in the ocean and...

Twin Agent: Context Residual Compression for Privilege Separated Agents

Large language model LLM agents are vulnerable to security risks, such as prompt injection attacks from untrusted context that manipulate downstream reasoning and tool use. Existing secure-by-design approaches mitigate this risk by separating untrusted observations from privileged execution and...

Amazon Linux 2 : amazon-ssm-agent, --advisory ALAS2-2026-3809 (ALAS-2026-3809)

The version of amazon-ssm-agent installed on the remote host is prior to 3.3.4624.0-1. It is, therefore, affected by multiple vulnerabilities as referenced in the ALAS2-2026-3809 advisory. An authenticated SSH client that repeatedly opened channels which were rejected by the server caused unbound...

PT-2026-62159

Name of the Vulnerable Software and Affected Versions Oracle Enterprise Manager Base Platform Agent Next Gen version 13.5 Oracle Enterprise Manager Base Platform Agent Next Gen version 24.1 Description An issue in the Agent Next Gen component allows an unauthenticated attacker with network access...

CVE-2026-57494

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/api prior to version 0.9.64, a low-privileged authenticated AgenticMail agent can enumerate another agent's pending/claimed tasks by supplying the target agent name to GET /api/agenticmail/tasks/pending?assignee=...

EUVD-2026-46122

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/api prior to version 0.9.64, a low-privileged authenticated AgenticMail agent can enumerate another agent's pending/claimed tasks by supplying the target agent name to GET /api/agenticmail/tasks/pending?assignee=...