CVE-2026-18236
A vulnerability in the Agent Development Kit (ADK) allows for continuation forgery in tool confirmations. An attacker who is able to manipul
CVSS
—
No CVSS
EPSS
—
KEV
—
Exploit Today
—
0-100
Published: Jul 29, 2026 · Last modified: Jul 29, 2026 · CWE-863
Not enough EPSS history yet.
A vulnerability in the Agent Development Kit (ADK) allows for continuation forgery in tool confirmations. An attacker who is able to manipulate or inject events into the session history can execute unauthorized tools by forging a tool confirmation response. This is possible because the framework did not verify if the target tool was registered to the executing agent, did not validate if the tool actually required confirmation, and did not match the confirmation arguments against the original tool call event in the history.
CVECVSSEPSSKEVRExploitTitleMod.
CVE-2026-674394.3 MED—
———OliveTin gives safe and simple access to predefined shell commands from a web interface. Prior to 3000.17.0, the service/internal/api/api.go StartActionAndWait and StartActionByGetAndWait endpoints return full LogEntry output after execution without enforcing the logs permission, allowing a user with exec permission but logs:false to read action output. This issue is fixed in version 3000.17.0.5hCVE-2026-659756.5 MED—
———Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. In versions 1.88.0 up to but not including 1.107.1 and 2.0.0b1 up to but not including 2.5.0, the UI adapters (AG-UI via Agent.to_ag_ui()/AGUIAdapter, and Vercel AI via VercelAIAdapter) use sanitize_messages to strip unresolved ("dangling") client-submitted tool calls from untrusted message history before it reaches the agent, a defense-in-depth default that prevents the agent from executing tool calls the model never emitted. However, the strip anchored to a message index computed before sanitization ran, so when a trailing client message sanitized to empty and was dropped (for example a client system message under the default manage_system_prompt='server'), a preceding assistant response carrying an unresolved tool call became the new tail and was dispatched without inspection. As a result, a remote client could cause a registered, non-approval server tool to run with client-supplied arguments rather than arguments the model produced. The impact is bounded by what the affected tools do and is most significant for applications that gate tool execution in a model-request hook (before_model_request / after_model_request), since a forged call skips the model turn and bypasses that guardrail; approval-gated tools (requires_approval=True) are not auto-executed by this path. This issue has been fixed in versions 1.107.1 and 2.5.0.5hCVE-2026-63365.3 MED—
———GitLab has remediated an issue in GitLab CE/EE affecting all versions from 16.6 before 19.0.5, 19.1 before 19.1.3, and 19.2 before 19.2.1 that under certain conditions could have allowed an unauthorized user to view project import source information due to a missing authorization check.6hCVE-2025-145623.1 LOW—
———GitLab has remediated an issue in GitLab CE/EE affecting all versions from 10.6 before 19.0.5, 19.1 before 19.1.3, and 19.2 before 19.2.1 that under certain conditions could have allowed an authenticated user with developer-role permissions to commit changes to a project after being removed as a member, due to improper authorization checks on merge request collaboration settings.6hCVE-2026-54693——
———ZITADEL is an open source identity management platform. From 2.43.0 through 2.71.19, from 3.0.0 until 3.4.11, and from 4.0.0 until 4.15.1, the email and phone self-management API paths in internal/command/user_v2_email.go, internal/command/user_v2_phone.go, and internal/command/user_v2_human.go allowed users to request returned verification codes without the required permission, allowing users to claim ownership of email addresses or phone numbers they do not control and bypass email-based or phone-based security policies. This issue is fixed in versions 3.4.11 and 4.15.1.8hCVE-2026-182557.2 HIG—
———A flaw was found in Quay. A user configured in GLOBAL_READONLY_SUPER_USERS is able to view robot account tokens for repositories they are not a member of, allowing an attacker with read-only superuser privileges to impersonate any robot account.7h