CVE-2026-56259 Crawl4AI - LLM Credential Exfiltration via base_url and Environment Variable Resolution

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-2026-3443

Crawl4AI before 0.8.7 contains a server-side request forgery SSRF vulnerability in the Docker API server's /crawl/job and /llm/job endpoints, which accept webhook URLs without destination validation. An attacker can supply webhook URLs pointing to private or internal IP ranges, Docker networks, o...

patchtriage

PatchTriage !CIhttps://github.com/d01ki/patchtriage/actio...

CVE-2026-55615 Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, Neo4jChatAgent passes LLM-generated Cypher queries straight to the Neo4j driver with no validation, no statement-type allowlist, and no opt-out gate. The query text is influenceable by prompt...

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-2026-43752

An authenticated administrator may be able to achieve arbitrary code execution on the host system by uploading a malicious file through the Open Source LLM setup feature in the Admin Console. This vulnerability has been addressed in FileMaker Server 26.0.1...

CVE-2026-43752

An authenticated administrator may be able to achieve arbitrary code execution on the host system by uploading a malicious file through the Open Source LLM setup feature in the Admin Console. This vulnerability has been addressed in FileMaker Server 26.0.1...

DRUPAL-CONTRIB-2026-076

The AI SEO/GEO Analyzer module generates SEO/GEO analysis reports by sending content of an entity including its comments to an LLM, then converts the model's Markdown response to HTML and stores it for display to privileged users. The generated HTML was rendered without passing through Drupal's...

AI SEO/GEO Analyzer - Moderately critical - Cross-site Scripting - SA-CONTRIB-2026-076

The AI SEO/GEO Analyzer module generates SEO/GEO analysis reports by sending content of an entity including its comments to an LLM, then converts the model's Markdown response to HTML and stores it for display to privileged users. The generated HTML was rendered without passing through Drupal's...

CVE-2026-58473

Cognee before 1.2.0 contains an improper access control vulnerability that allows unauthenticated attackers to overwrite the global LLM provider configuration by self-registering an account and calling the settings endpoint, which performs no admin or superuser check. Attackers can redirect all L...

CVE-2026-58473 Cognee < 1.2.0 Unauthorized LLM Configuration Overwrite via /api/v1/settings

Cognee before 1.2.0 contains an improper access control vulnerability that allows unauthenticated attackers to overwrite the global LLM provider configuration by self-registering an account and calling the settings endpoint, which performs no admin or superuser check. Attackers can redirect all L...

CVE-2026-58473

CVE-2026-58473 (Cognee) vulnerability affects Cognee prior to 1.2.0. An improper access-control flaw allows unauthenticated attackers to overwrite the global LLM provider configuration by self-registering an account and calling the settings endpoint, which lacks admin/superuser checks. This enabl...

GO-2026-5925 Suspended Coder users retain access to AI Bridge LLM proxy endpoints in github.com/coder/coder

Suspended Coder users retain access to AI Bridge LLM proxy endpoints in github.com/coder/coder...

LlamaIndex Improper Handling of Exceptional Conditions vulnerability

A vulnerability in the LangChainLLM class of the run-llama/llamaindex repository, version v0.12.5, allows for a Denial of Service DoS attack. The streamcomplete method executes the llm using a thread and retrieves the result via the getresponsegen method of the StreamingGeneratorCallbackHandler...

PYSEC-2026-1934 Spacy-LLM Server-Side Template Injection (SSTI) vulnerability

A Server-Side Template Injection SSTI vulnerability in Spacy-LLM v0.7.2 allows attackers to execute arbitrary code via injecting a crafted payload into the template field...

PYSEC-2026-2024 vLLM denial of service vulnerability

A flaw was found in the vLLM library. A completions API request with an empty prompt will crash the vLLM API server, resulting in a denial of service...

PT-2026-56255

Name of the Vulnerable Software and Affected Versions Cognee versions prior to 1.2.0 Description Improper access control allows unauthenticated attackers to overwrite the global LLM provider configuration. By self-registering an account and calling the '/api/v1/settings' endpoint, which lacks adm...

CVE-2026-55574

CVE-2026-55574 affects vLLM prior to 0.24.0, where structured_outputs.regex passes an unguarded user-supplied regex to grammar backends (xgrammar and outlines). In xgrammar, the string reaches the regex compiler without a timeout guard; in outlines, validation overlooks regex complexity (e.g., ne...

Information Exposure

Overview Affected versions of this package are vulnerable to Information Exposure in the logging process when the DEBUG loglevel is enabled. An attacker can access sensitive information, such as API keys or LLM response data, by reading log files generated under these conditions. This is only...

CVE-2026-44934

A information disclosure when DEBUG loglevel is set in SUSE Rancher AI Agent 1.0 before 1.0.2 could leak API keys or LLM response text with potential sensitive data into logfiles, allowing local attackers to misuse respective gained data or credentials...