A vulnerability (CVE-2026-126995) was discovered in tjake Jlama versions up to 0.8.4 and 0.9.0-beta affecting the SafeTensorIndex.loadWeights function in SafeTensorIndex.java. The vulnerability allows for path traversal via manipulation of the weightmap argument, making it susceptible to remote attacks. An exploit has been publicly disclosed and the project has not yet responded to an early issue report. This vulnerability matters to people building or operating AI agents using tjake Jlama as it may allow unauthorized access to sensitive data or system resources.

A vulnerability (CVE-2026-126767) was found in OpsTree REMS versions up to 1.0.0, affecting its chat assistant feature. The vulnerability, a prompt injection issue, allows authenticated users to access the system's internal prompt by submitting specially crafted chat input to the /api/v1/rca/chat endpoint. This enables attackers to bypass the assistant's rules and obtain sensitive orchestration instructions, facilitating further prompt injection attacks. This matters to AI developers and operators as it compromises the security of the chat assistant, potentially allowing malicious users to manipulate the system and gain unauthorized access to internal information.

A vulnerability (CVE-2026-124503) was identified in the sooperset mcp-atlassian library, affecting versions up to 0.24.0. The issue arises from a path traversal vulnerability in the validate_safe_path function in src/mcp-atlassian/utils/io.py, making it susceptible to remote attacks. An exploit is publicly available, and upgrading to version 0.24.1 is recommended to mitigate this issue.

A vulnerability was discovered in the agentmemory module of the SAP Cloud SDK for Python prior to version 0.50.0. The module fails to properly validate the tenant parameter, allowing an attacker to manipulate the filesystem path and access another tenant's secrets. This can occur when a malicious tenant ID contains path traversal sequences, enabling unauthorized access to sensitive credentials such as OAuth client IDs and client secrets.

A vulnerability (CVE-2026-120012) was discovered in the SAP Cloud SDK for AI (JavaScript), allowing an attacker to obtain sensitive authentication credentials from error messages generated under specific conditions. This occurs when a low-privileged user accesses logs or forwarded error output after a failure event triggered by a higher-privileged user. The attacker must wait for the token's limited lifetime to exploit the vulnerability, which could result in a high impact on confidentiality, integrity, and availability. This vulnerability matters to AI developers and operators as it may allow unauthorized access to sensitive credentials, compromising system security and potentially leading to data breaches or service disruptions.

IBM ContextForge MCP Gateway versions 1.0.0 through 1.0.11 are vulnerable to a denial-of-service (DoS) attack due to improper slug normalization, where a remote authenticated attacker can cause a tool name collision, leading to a denial-of-service condition. This vulnerability is relevant to developers and operators of AI agents using IBM ContextForge MCP Gateway, as it may be used in conjunction with other AI tools, and a successful attack could disrupt the functionality of these agents, potentially causing operational disruptions or data loss.

A critical vulnerability (CVE-2025-1837) has been identified in IBM Watsonx Orchestrate with Watsonx Assistant Cartridge, affecting versions 4.8.4 through 4.8.5 and 5.0.0 through 5.4.2. The vulnerability allows an authenticated user to perform unauthorized actions due to improper trust of server-side permission methods. This issue matters to developers and operators of AI agents that utilize Watsonx Orchestrate, as it enables a malicious actor to bypass security controls and potentially compromise the security and integrity of their AI systems.

IBM has released a security advisory (CVE-2025-0166) regarding multiple vulnerabilities in the Watsonx Orchestrate Cartridge for Cloud Pak for Data. Specifically, versions 4.8.4 through 4.8.5 and 5.0.0 through 5.4.2 are affected. These vulnerabilities can disclose sensitive source code information that should be inaccessible, potentially exposing confidential data. Affected users should update to a patched version of the Cartridge to mitigate the risk of exploitation. The update is crucial for developers and operators of AI agents that rely on the Watsonx Orchestrate Cartridge to prevent potential security breaches and maintain data confidentiality.

A vulnerability (CVE-2026-123881) exists in OpenBMB Internet of Agents, affecting the Message Handler component's `fetch_chat_record` function in `app.py`. The issue arises from improper access control due to manipulation of the `commid` argument, allowing remote attacks. The vulnerability is exploitable in versions up to 9d78e88e47160eb42ee1ee8538c05e1c2c47877a. This matters to developers and operators as it may enable unauthorized access to sensitive information, highlighting the need for prompt patching and secure coding practices.

A vulnerability (CVE-2026-58490) was identified in Tracecat, a security automation platform, affecting Docker Compose deployments with SAML enabled. Versions 0.37.0 through 1.0.0-beta.49 were vulnerable, allowing an attacker to submit a forged unsigned SAML response and obtain an existing user's session, potentially leading to superadmin account takeover. This exploit does not create new users when SAML user creation is disabled and does not affect Fargate or Helm deployments. Version 1.0.0-beta.49 resolves the issue by requiring signed assertions and responses.

PyTorch's TorchServe has a vulnerability in all versions where an attacker can exploit a predictable extraction directory in /tmp to swap the model handler and execute code as the TorchServe service account, resulting in local privilege escalation. This allows a local user to access sensitive information and potentially take control of the system. This vulnerability matters to people building and operating AI agents because it enables an attacker to bypass security controls and access sensitive data or disrupt the operation of the AI system.

A vulnerability (CVE-2026-75598) was identified in the Gradle Shadow plugin, affecting versions prior to 9.6.0. The issue arises from the plugin not validating ZIP entry names before writing them to the output archive, allowing malicious dependencies to potentially cause path traversal. This can result in attacker-controlled files being written outside the intended destination when the resulting archive is extracted without path traversal protection. To mitigate this issue, developers should upgrade the Gradle Shadow plugin to version 9.6.0 or later.

A vulnerability (CVE-2026-123989) was discovered in ESEngine DeepSeek-Reasonix version 1.33.0 and earlier. The loadGitStatus function in the build.rs file of the Build Script Execution component is affected, allowing remote attackers to exploit permission issues. To mitigate this, users should upgrade to version 1.34.0, which includes a patch (a54659c2c5b0f4e57aae2b44d41f421c6a71e8cf).