PT-2026-121505

Name of the Vulnerable Software and Affected Versions LiteLLM versions 1.87.0 through 1.100.3 LiteLLM versions 1.101.0 through 1.101.2 LiteLLM versions 1.102.0 through 1.102.1 LiteLLM versions 1.103.0 LiteLLM versions 1.104.0-rc.0 through 1.104.0-rc.1 Description LiteLLM reuses a single...

OpenCode Console Breach May Have Exposed OpenAI, Anthropic, and Google API Keys

An intruder reached a legacy system at OpenCode on the night of October 16 and may have exposed the third-party AI provider keys that users had saved in OpenCode Console, the company said. Console is OpenCode's optional hosted service: a workspace saves its own OpenAI, Anthropic, or Google key...

EUVD-2026-102435

EnergizeLab station-middleware NestJS Docker images 1.6.5 through 1.8.2 do not check user roles on administrative APIs. Any authenticated low-privilege user can retrieve AI provider keys and change configuration and object-store contents...

CVE-2026-105039

EnergizeLab station-middleware (NestJS) Docker images versions 1.6.5 through 1.8.2 are vulnerable to a Missing Authorization (CWE-862) flaw. The application fails to perform role checks on administrative APIs, allowing any authenticated low-privilege user to perform unauthorized actions. Attacker...

CVE-2026-105039 EnergizeLab Station Middleware Admin APIs Missing Role Checks

EnergizeLab station-middleware NestJS Docker images 1.6.5 through 1.8.2 do not check user roles on administrative APIs. Any authenticated low-privilege user can retrieve AI provider keys and change configuration and object-store contents...

CVE-2026-105039 EnergizeLab Station Middleware Admin APIs Missing Role Checks

EnergizeLab station-middleware NestJS Docker images 1.6.5 through 1.8.2 do not check user roles on administrative APIs. Any authenticated low-privilege user can retrieve AI provider keys and change configuration and object-store contents...

PT-2026-115226

Name of the Vulnerable Software and Affected Versions EnergizeLab station-middleware NestJS Docker images versions 1.6.5 through 1.8.2 Description Insufficient authorization checks on administrative APIs allow authenticated users with low privileges to perform unauthorized actions. This includes...

CVE-2026-105039: Missing Authorization

EnergizeLab station-middleware NestJS Docker images 1.6.5 through 1.8.2 do not check user roles on administrative APIs. Any authenticated low-privilege user can retrieve AI provider keys and change configuration and object-store contents...

EnergizeLab station-middleware authorization issue vulnerability

The EnergizeLab station-middleware versions 1.6.5 to 1.8.2 have authorization-related vulnerabilities. This issue arises from the management API not checking user roles, which may allow any authenticated, low-privilege user to obtain AI provider keys and alter configuration settings as well as...

CVE-2026-110208 Wukong AICRM through 20260610 Missing Authorization in System Configuration APIs Exposes Stored AI Provider Keys

Wukong AICRM through 20260610 contains a missing authorization vulnerability in the /systemConfig controller that allows any authenticated user to read the stored AI provider API key. Attackers can request GET /systemConfig/byType/ai for the cleartext key, or send a chosen apiUrl to...

CVE-2026-110208

Wukong AICRM versions through 20260610 are vulnerable to a missing authorization flaw in the /systemConfig controller. This vulnerability allows any authenticated user to access sensitive AI provider API keys in cleartext. Specifically, an attacker can perform a GET request to /systemConfig/byTyp...

CVE-2026-110208 Wukong AICRM through 20260610 Missing Authorization in System Configuration APIs Exposes Stored AI Provider Keys

Wukong AICRM through 20260610 contains a missing authorization vulnerability in the /systemConfig controller that allows any authenticated user to read the stored AI provider API key. Attackers can request GET /systemConfig/byType/ai for the cleartext key, or send a chosen apiUrl to...

CVE-2026-82640 browser-use web-ui 2.0.0 through 3.0.0 Cleartext API Key Storage

browser-use web-ui versions 2.0.0 through 3.0.0 write configured LLM API keys to disk in cleartext without encryption or access restrictions. Attackers with read access to the temporary settings directory can recover provider API keys from predictably-named JSON files...

CVE-2026-67425: Insertion of Sensitive Information Into Sent Data

Flyto2 Core is an execution kernel for automation and AI-agent workflows. Prior to 2.26.6, llm.chat reads provider keys such as OPENAIAPIKEY and ANTHROPICAPIKEY from the environment and sends them in the Authorization: Bearer header to caller-controlled baseurl, allowing an attacker to receive th...

CVE-2026-56259

Crawl4AI before 0.8.8 contains credential exfiltration vulnerabilities in the Docker API server that allow attackers to redirect LLM API calls to attacker-controlled endpoints and read arbitrary environment variables. Attackers can exploit the unauthenticated /md, /llm, and /llm/job endpoints by...

PYSEC-0000-CVE-2026-56259

Crawl4AI before 0.8.8 contains credential exfiltration vulnerabilities in the Docker API server that allow attackers to redirect LLM API calls to attacker-controlled endpoints and read arbitrary environment variables. Attackers can exploit the unauthenticated /md, /llm, and /llm/job endpoints by...

EUVD-2026-42656

Ruflo is an agent meta-harness for Claude Code and Codex. Prior to 3.16.3, ruflo's default docker-compose deployment exposed the MCP bridge POST /mcp and POST /mcp/:group endpoints without authentication, allowing an unauthenticated network attacker to invoke tools/call to terminalexecute, obtain...

CVE-2026-59726 Ruflo: Unauthenticated RCE in MCP bridge default docker-compose deployment

Ruflo is an agent meta-harness for Claude Code and Codex. Prior to 3.16.3, ruflo's default docker-compose deployment exposed the MCP bridge POST /mcp and POST /mcp/:group endpoints without authentication, allowing an unauthenticated network attacker to invoke tools/call to terminalexecute, obtain...

CVE-2026-59726 Ruflo: Unauthenticated RCE in MCP bridge default docker-compose deployment

Ruflo is an agent meta-harness for Claude Code and Codex. Prior to 3.16.3, ruflo's default docker-compose deployment exposed the MCP bridge POST /mcp and POST /mcp/:group endpoints without authentication, allowing an unauthenticated network attacker to invoke tools/call to terminalexecute, obtain...

CVE-2026-59726

Ruflo is an agent meta-harness for Claude Code and Codex. Prior to 3.16.3, ruflo's default docker-compose deployment exposed the MCP bridge POST /mcp and POST /mcp/:group endpoints without authentication, allowing an unauthenticated network attacker to invoke tools/call to terminalexecute, obtain...