PT-2026-59552

PraisonAI’s MCP Model Context Protocol integration allows spawning background servers via stdio using user-supplied command strings e.g., MCP"npx -y @smithery/cli ...". These commands are executed through Python’s subprocess module. By default, the implementation forwards the entire parent proces...

PT-2026-59353

Summary Broken Access Control in Tool Valves Open WebUI supports function calling through "Tools". Function calling allows an LLM to reliably connect to external tools and interact with external APIs. Exemplary use-cases include connecting to an internal knowledge base, retrieving emails from an...

PT-2026-59252

LiteLLM prior to 1.83.14 allows an authenticated internal user to create API keys with access to routes that their role does not permit. When generating a key, the allowed routes field is stored without verifying that the specified routes fall within the user's own permissions. A key created with...

CVE-2026-62327: Missing Authentication for Critical Function

9Router through version 0.4.41 contain an unauthenticated information disclosure vulnerability that allows remote attackers to retrieve plaintext API keys for all connected AI provider accounts by sending a single unauthenticated request to the /api/usage/stats endpoint. Attackers can exploit the...

The vulnerability of the is_user_channelmember() function in the Open WebUI artificial intelligence-based web interface allows a intruder to bypass existing security mechanisms and gain access to read and modify data.

The vulnerability of the isuserchannelmember function in the Open WebUI artificial intelligence-based web interface is related to the lack of restrictions on access to API keys. Exploiting this vulnerability could allow a malicious actor to bypass existing security mechanisms and gain access to...

PYSEC-2026-3448

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-2026-3448

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...

MAL-2026-10170 Malicious code in paysafe-kyc (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 626046f7b80cd91ce41e057b4bdab7b5bbb30b7fbceb0284894287cfd441c624 The package presents itself as the Paysafe KYC identity verification SDK but does not call any Paysafe API. PaysafeClient's payments/customers method...

CVE-2026-61450

Grav before 2.0.2 contains a Twig sandbox bypass that allows a page author any admin.pages user, or anyone able to write to user/pages to exfiltrate configuration secrets. Although the sandbox replaces the 'config' variable with a redacted facade and strips Config::get/toArray from the method...

EUVD-2026-42726

Hermes WebUI before 0.51.307 contains an authentication bypass vulnerability that allows unauthenticated remote attackers to circumvent local-origin IP restrictions on onboarding endpoints by supplying a spoofed X-Forwarded-For header with a loopback address. Attackers can exploit this bypass to...

CVE-2026-56335: Improper Access Control

Capgo before 12.128.2 contains an authorization bypass vulnerability where write-scoped API keys can directly mutate protected channel configuration fields through PostgREST by exploiting a null authentication check in the immutability trigger. Attackers with write API keys can modify sensitive...

CVE-2026-58122 Hermes WebUI < 0.51.307 Authentication Bypass via X-Forwarded-For Header Spoofing

Hermes WebUI before 0.51.307 contains an authentication bypass vulnerability that allows unauthenticated remote attackers to circumvent local-origin IP restrictions on onboarding endpoints by supplying a spoofed X-Forwarded-For header with a loopback address. Attackers can exploit this bypass to...

CVE-2026-58122 Hermes WebUI < 0.51.307 Authentication Bypass via X-Forwarded-For Header Spoofing

Hermes WebUI before 0.51.307 contains an authentication bypass vulnerability that allows unauthenticated remote attackers to circumvent local-origin IP restrictions on onboarding endpoints by supplying a spoofed X-Forwarded-For header with a loopback address. Attackers can exploit this bypass to...

PT-2026-56988

Name of the Vulnerable Software and Affected Versions Hermes WebUI versions prior to 0.51.307 Description An authentication bypass exists that allows unauthenticated remote attackers to circumvent local-origin IP restrictions on onboarding endpoints. This is achieved by supplying a spoofed...

CVE-2026-59706 mem0 - Unauthenticated Config API Exposure and SSRF via ollama_base_url

mem0 contains unauthenticated config API endpoints that expose LLM API keys in plaintext and allow server-side request forgery via attacker-controlled ollamabaseurl parameter. Unauthenticated attackers can retrieve stored secrets like OpenAI API keys via GET /api/v1/config/ or trigger SSRF attack...

CVE-2026-59706 mem0 - Unauthenticated Config API Exposure and SSRF via ollama_base_url

mem0 contains unauthenticated config API endpoints that expose LLM API keys in plaintext and allow server-side request forgery via attacker-controlled ollamabaseurl parameter. Unauthenticated attackers can retrieve stored secrets like OpenAI API keys via GET /api/v1/config/ or trigger SSRF attack...

CVE-2026-59706

CVE-2026-59706 (mem0) is a vulnerability where unauthenticated config API endpoints expose LLM API keys in plaintext and enable server-side request forgery. The issue arises from an attacker-controllable ollama_base_url parameter, allowing SSRF to internal addresses (e.g., cloud IMDS) via PUT /ap...

CVE-2026-59706 mem0 - Unauthenticated Config API Exposure and SSRF via ollama_base_url

mem0 contains unauthenticated config API endpoints that expose LLM API keys in plaintext and allow server-side request forgery via attacker-controlled ollamabaseurl parameter. Unauthenticated attackers can retrieve stored secrets like OpenAI API keys via GET /api/v1/config/ or trigger SSRF attack...

CVE-2026-55435

Coder allows organizations to provision remote development environments via Terraform. Starting in version 2.30.0 and prior to versions 2.32.7, 2.33.8, and 2.34.2, AI Bridge proxy endpoints authenticate via Server.IsAuthorized in coderd/aibridgedserver, which validates key format, expiry, secret...

CVE-2026-55435

CVE-2026-55435 affects Coder’s AI Bridge proxy endpoints. The vulnerability stems from Server.IsAuthorized not checking whether a suspended account is active, so an unexpired API key issued to a suspended user remains usable until the key is deleted. Impact is limited to already-issued keys; no n...