diff --git a/advisories/github-reviewed/2025/05/GHSA-93m4-mfpg-c3xf/GHSA-93m4-mfpg-c3xf.json b/advisories/github-reviewed/2025/05/GHSA-93m4-mfpg-c3xf/GHSA-93m4-mfpg-c3xf.json index bd6edf7fc59..6ff4de9dea1 100644 --- a/advisories/github-reviewed/2025/05/GHSA-93m4-mfpg-c3xf/GHSA-93m4-mfpg-c3xf.json +++ b/advisories/github-reviewed/2025/05/GHSA-93m4-mfpg-c3xf/GHSA-93m4-mfpg-c3xf.json @@ -1,9 +1,11 @@ { "schema_version": "1.4.0", "id": "GHSA-93m4-mfpg-c3xf", - "modified": "2025-05-28T17:36:55Z", + "modified": "2025-05-29T21:07:48Z", "published": "2025-05-28T17:36:55Z", - "aliases": [], + "aliases": [ + "CVE-2025-48936" + ], "summary": "ZITADEL Allows Account Takeover via Malicious X-Forwarded-Proto Header Injection", "details": "### Impact\n\nA potential vulnerability exists in ZITADEL's password reset mechanism. ZITADEL utilizes the Forwarded or X-Forwarded-Host header from incoming requests to construct the URL for the password reset confirmation link. This link, containing a secret code, is then emailed to the user.\n\nIf an attacker can manipulate these headers (e.g., via host header injection), they could cause ZITADEL to generate a password reset link pointing to a malicious domain controlled by the attacker. If the user clicks this manipulated link in the email, the secret reset code embedded in the URL can be captured by the attacker. This captured code could then be used to reset the user's password and gain unauthorized access to their account.\n\nIt's important to note that this specific attack vector is mitigated for accounts that have Multi-Factor Authentication (MFA) or Passwordless authentication enabled.\n\n### Patches\n\nPatched version ensure proper validation of the headers and do not allow downgrading from https to http.\n\n3.x versions are fixed on >=[3.2.2](https://github.com/zitadel/zitadel/releases/tag/v3.2.2)\n2.71.x versions are fixed on >=[2.71.11](https://github.com/zitadel/zitadel/releases/tag/v2.71.11)\n2.x versions are fixed on >=[2.70.12](https://github.com/zitadel/zitadel/releases/tag/v2.70.12)\n\n### Workarounds\n\nThe recommended solution is to update ZITADEL to a patched version.\n\nA ZITADEL fronting proxy can be configured to delete all Forwarded and X-Forwarded-Host header values before sending requests to ZITADEL self-hosted environments.\n\n### Questions\n\nIf you have any questions or comments about this advisory, please email us at [security@zitadel.com](mailto:security@zitadel.com)\n\n### Credits\n\nThanks to Amit Laish – GE Vernova for finding and reporting the vulnerability.", "severity": [ diff --git a/advisories/github-reviewed/2025/05/GHSA-w6q7-j642-7c25/GHSA-w6q7-j642-7c25.json b/advisories/github-reviewed/2025/05/GHSA-w6q7-j642-7c25/GHSA-w6q7-j642-7c25.json index 58fbbdd3f73..29c19224987 100644 --- a/advisories/github-reviewed/2025/05/GHSA-w6q7-j642-7c25/GHSA-w6q7-j642-7c25.json +++ b/advisories/github-reviewed/2025/05/GHSA-w6q7-j642-7c25/GHSA-w6q7-j642-7c25.json @@ -1,9 +1,11 @@ { "schema_version": "1.4.0", "id": "GHSA-w6q7-j642-7c25", - "modified": "2025-05-28T17:49:33Z", + "modified": "2025-05-29T21:07:38Z", "published": "2025-05-28T17:49:33Z", - "aliases": [], + "aliases": [ + "CVE-2025-48887" + ], "summary": "vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`", "details": "## Summary\n\nA Regular Expression Denial of Service (ReDoS) vulnerability exists in the file [`vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py`](https://github.com/vllm-project/vllm/blob/main/vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py) of the vLLM project. The root cause is the use of a highly complex and nested regular expression for tool call detection, which can be exploited by an attacker to cause severe performance degradation or make the service unavailable.\n\n## Details\n\nThe following regular expression is used to match tool/function call patterns:\n```\nr\"\\[([a-zA-Z]+\\w*\\(([a-zA-Z]+\\w*=.*,\\s*)*([a-zA-Z]+\\w*=.*\\s)?\\),\\s*)*([a-zA-Z]+\\w*\\(([a-zA-Z]+\\w*=.*,\\s*)*([a-zA-Z]+\\w*=.*\\s*)?\\)\\s*)+\\]\"\n```\nThis pattern contains multiple nested quantifiers (`*`, `+`), optional groups, and inner repetitions which make it vulnerable to catastrophic backtracking.\n\n**Attack Example:**\nA malicious input such as \n```\n[A(A=\t)A(A=,\t\t)A(A=,\t\t)A(A=,\t\t)... (repeated dozens of times) ...]\n\nor\n\n\"[A(A=\" + \"\\t)A(A=,\\t\" * repeat\n```\n\n\n\ncan cause the regular expression engine to consume CPU exponentially with the input length, effectively freezing or crashing the server (DoS).\n\n**Proof of Concept:**\nA Python script demonstrates that matching such a crafted string with the above regex results in exponential time complexity. Even moderate input lengths can bring the system to a halt.\n\n```\nLength: 22, Time: 0.0000 seconds, Match: False\nLength: 38, Time: 0.0010 seconds, Match: False\nLength: 54, Time: 0.0250 seconds, Match: False\nLength: 70, Time: 0.5185 seconds, Match: False\nLength: 86, Time: 13.2703 seconds, Match: False\nLength: 102, Time: 319.0717 seconds, Match: False\n```\n\n## Impact\n\n- **Denial of Service (DoS):** An attacker can trigger a denial of service by sending specially crafted payloads to any API or interface that invokes this regex, causing excessive CPU usage and making the vLLM service unavailable.\n- **Resource Exhaustion and Memory Retention:** As this regex is invoked during function call parsing, the matching process may hold on to significant CPU and memory resources for extended periods (due to catastrophic backtracking). In the context of vLLM, this also means that the associated KV cache (used for model inference and typically stored in GPU memory) is not released in a timely manner. This can lead to GPU memory exhaustion, degraded throughput, and service instability.\n- **Potential for Broader System Instability:** Resource exhaustion from stuck or slow requests may cascade into broader system instability or service downtime if not mitigated.\n\n## Fix\n\n* https://github.com/vllm-project/vllm/pull/18454\n* Note that while this change has significantly improved performance, this regex may still be problematic. It has gone from exponential time complexity, O(2^N), to O(N^2).", "severity": [