VulnerabilityPublished 13 Aug 2026Updated 14 Aug 2026

CVE-2026-73555: vllm · Generation of Error Message Containing Sensitive Information

Affects vllmSource CVE Database V5

Compare

Not known to be exploited · CVSS 5.3 Medium : upgrade to 0.26.0 when convenient.

Data as of 12 Nov 2026, 23:24 UTC

CVSS 3.1 base score

5.3Medium

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.4% chance of exploitation in 30 days – higher than 36% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 0.26.0

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: None
Scope: Unchanged
Confidentiality: Low
Integrity: None
Availability: None

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files to carry out an attack.
User Interaction: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Unchanged: An exploited vulnerability can only affect resources managed by the same security authority. In this case, the vulnerable component and the impacted component are either the same, or both are managed by the same security authority.
Confidentiality: Low: There is some loss of confidentiality. Access to some restricted information is obtained, but the attacker does not have control over what information is obtained, or the amount or kind of loss is limited. The information disclosure does not cause a direct, serious loss to the impacted component.
Integrity: None: There is no loss of integrity within the impacted component.
Availability: None: There is no impact to availability within the impacted component.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 13 Aug 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 13 Nov 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponized: A Metasploit exploit module or Exploit-DB entry exists (Metasploit scanner modules do not count), or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade vllm and vllm-project/vllm to 0.26.0.

Affected software

Product	Affected	Fixed in
vllm-projectvllm	Affected <0.26.0	Fixed in 0.26.0
GitHubvllm-project/vllm`pkg:github/vllm-project/vllm`Other threats	Affected <0.26.0	Fixed in 0.26.0

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

A fix is available in vLLM version 0.26.0 that changes the validation exception handler to avoid returning traceback-style strings in error responses. Users should upgrade to vLLM 0.26.0 or later. Alternatively, deploying vLLM behind a reverse proxy that rewrites error responses to remove file paths can mitigate the issue but is fragile. No other mitigations are recommended as the root cause is addressed in the official fix.

Description

vLLM versions prior to 0.26.0 have a vulnerability where malformed API requests cause error messages to leak sensitive internal information such as file paths, line numbers, OS username, home directory, Python version, and internal package structure. This occurs because the error handler converts validation exceptions to strings that include traceback details, which are insufficiently sanitized before being returned in HTTP responses. This information disclosure can aid attackers in fingerprinting the environment and crafting targeted exploits. The issue affects all POST endpoints accepting JSON bodies. A fix is available in vLLM 0.26.0 that changes the error handling to avoid leaking such details.

Impact

An unauthenticated attacker can obtain sensitive internal information including OS username, home directory path, virtual environment path, Python version, internal source file paths with line numbers, and handler function names. This information disclosure can facilitate targeted attacks by enabling precise version fingerprinting and reducing the attack surface. The vulnerability does not allow direct code execution or data modification but leaks environment details that aid attackers.

Summary

When vLLM receives malformed JSON requests, FastAPI raises a Pydantic RequestValidationError. The vLLM error handler converts this exception to a string including internal file paths and line numbers, which are returned in HTTP responses. The existing sanitization removes memory addresses but not file path and line number patterns, resulting in leakage of sensitive environment details such as OS username, home directory, Python version, internal package structure, and handler function names. This vulnerability affects all JSON POST endpoints and enables unauthenticated attackers to fingerprint the system and narrow attack surfaces. The issue was fixed by changing the error handler to construct error messages from structured error data rather than stringifying the exception, or alternatively by improving the sanitization regex.

CWE-209Generation of Error Message Containing Sensitive Information (opens in a new tab)
Base weaknessLikelihood of exploit: HighOWASP Top 10 A10:2025: Mishandling of Exceptional Conditions (opens in a new tab)
The product generates an error message that includes sensitive information about its environment, users, or associated data.
Implementation
Ensure that error messages only contain minimal details that are useful to the intended audience and no one else. The messages need to strike the balance between being too cryptic (which can confuse users) or being too detailed (which may reveal more than intended).
Implementation
Handle exceptions internally and do not display errors containing potentially sensitive information to a user.
Implementation · Attack Surface Reduction
Use naming conventions and strong types to make it easier to spot when sensitive data is being used. When creating structures, objects, or other complex entities, separate the sensitive and non-sensitive data as much as possible.
OWASP Cheat Sheets
Error Handling (opens in a new tab)
Logging (opens in a new tab)
OWASP ASVS 4.0.3
V8.3.4 (opens in a new tab)
V14.3.3 (opens in a new tab)
V7.3.3 (opens in a new tab)
Attack patterns
Fuzzing for application mapping (opens in a new tab)
Padding Oracle Crypto Attack (opens in a new tab)
Query System for Information (opens in a new tab)
Blind SQL Injection (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 13 Sep 2026, 13:04 UTC

WeaknessesCWE-209

Technical details

References

Community reviews

Related threats