CVE-2025-48887
published 2025-05-30CVE-2025-48887: vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the file…
PriorityP433medium6.5CVSS 3.1
AVNACLPRLUINSUCNINAH
EPSS
0.43%
34.2th percentile
vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the file `vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py` of versions 0.6.4 up to but excluding 0.9.0. 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. The pattern contains multiple nested quantifiers, optional groups, and inner repetitions which make it vulnerable to catastrophic backtracking. Version 0.9.0 contains a patch for the issue.
Affected
4 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| vllm-project | vllm | — | — |
| vllm | vllm | >= 0 < 4fc1bf813ad80172c1db31264beaef7d93fe0601 | 4fc1bf813ad80172c1db31264beaef7d93fe0601 |
| vllm | vllm | >= 0.6.4 < 0.9.0 | 0.9.0 |
| vllm | vllm | >= 0.6.4 < 0.9.0 | 0.9.0 |
CVSS provenance
nvdv3.16.5MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
vendor_redhat6.5MEDIUM
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
OSV
CVE-2025-48887: vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the file `
osv·2025-05-30
CVE-2025-48887 CVE-2025-48887: vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the file `
vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the file `vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py` of versions 0.6.4 up to but excluding 0.9.0. 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. The pattern contains multiple nested quantifiers, optional groups, and inner repetitions which make it vulnerable to catastrophic backtracking. Version 0.9.0 contains a patch for the issue.
GHSA
vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`
ghsa·2025-05-28
CVE-2025-48887 [MEDIUM] CWE-1333 vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`
vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`
## Summary
A 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.
## Details
The following regular expression is used to match tool/function call patterns:
```
r"\[([a-zA-Z]+\w*\(([a-zA-Z]+\w*=.*,\s*)*([a-zA-Z]+\w*=.*\s)?\),\s*)*([a-zA-Z]+\w
OSV
vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`
osv·2025-05-28
CVE-2025-48887 [MEDIUM] vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`
vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`
## Summary
A 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.
## Details
The following regular expression is used to match tool/function call patterns:
```
r"\[([a-zA-Z]+\w*\(([a-zA-Z]+\w*=.*,\s*)*([a-zA-Z]+\w*=.*\s)?\),\s*)*([a-zA-Z]+\w
Red Hat
vllm: vLLM has a Regular Expression Denial of Service (ReDoS) Vulnerability
vendor_redhat·2025-05-30·CVSS 6.5
CVE-2025-48887 [MEDIUM] CWE-1333 vllm: vLLM has a Regular Expression Denial of Service (ReDoS) Vulnerability
vllm: vLLM has a Regular Expression Denial of Service (ReDoS) Vulnerability
vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the file `vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py` of versions 0.6.4 up to but excluding 0.9.0. 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. The pattern contains multiple nested quantifiers, optional groups, and inner repetitions which make it vulnerable to catastrophic backtracking. Version 0.9.0 contains a patch for the issue.
A regular expression denial of service (ReDoS) flaw was found i
Suricata
ET WEB_SPECIFIC_APPS Fortinet FortiSwitch Unauthenticated Unverified Password Change (CVE-2024-48887)
suricata·2025-04-14·CVSS 9.8
CVE-2024-48887 [CRITICAL] ET WEB_SPECIFIC_APPS Fortinet FortiSwitch Unauthenticated Unverified Password Change (CVE-2024-48887)
ET WEB_SPECIFIC_APPS Fortinet FortiSwitch Unauthenticated Unverified Password Change (CVE-2024-48887)
Rule: alert http any any -> $HOME_NET any (msg:"ET WEB_SPECIFIC_APPS Fortinet FortiSwitch Unauthenticated Unverified Password Change (CVE-2024-48887)"; flow:established,to_server; http.method; content:"POST"; http.uri; bsize:12; content:"/change_pass"; fast_pattern; http.request_body; content:"|22|username|22|"; content:"|22|newpass|22|"; reference:url,github.com/cybersecplayground/CVE-2024-48887-FortiSwitch-Exploit; reference:cve,2024-48887; classtype:web-application-activity; sid:2061541; rev:1; metadata:attack_target Server, tls_state TLSDecrypt, created_at 2025_04_14, cve CVE_2024_48887, deployment Perimeter, deployment Internal, deployment SSLDecrypt, signature_severity Major, tag Ex
No public exploits indexed.
No writeups or analysis indexed.
2025-05-30
Published