CVE-2026-111392: Insufficient Verification of Data Authenticity in sgl-project sglang
Description
SGLang through 0.5.21 trusts caller-supplied mm_hashes values as the multimodal prefix-cache key, allowing remote attackers to poison cached KV entries across requests. Attackers can send a different image under a known or predicted hash via /generate to disclose another request's image content or corrupt victims' responses.
CVSS v4.0
Score 6.3medium
Affected software
sgl-project
sglang
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
SGLang versions 0.5.13 through 0.5.21 contain a vulnerability due to insufficient verification of caller-supplied mm_hashes values used as keys in the multimodal prefix-cache. An attacker can exploit this by sending a different image under a known or predicted hash via the /generate endpoint, which can cause cache poisoning. This enables disclosure of image content from other users' requests or corruption of responses sent to victims.
Potential Impact
The vulnerability allows remote attackers to poison the cache by supplying manipulated mm_hashes values. This can lead to unauthorized disclosure of image content from other requests or corrupted responses, potentially impacting confidentiality and integrity of data processed by the affected SGLang service. The CVSS 4.0 base score is 6.3 (medium severity), reflecting network attack vector with high attack complexity and partial attack prerequisites.
Mitigation Recommendations
No patch or official fix information is provided in the available data. Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until a fix is available, users should consider restricting access to the /generate endpoint or implementing additional validation on mm_hashes values to prevent cache poisoning.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-10-15T21:55:44.538Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6ad264092cdf04f656199531
Added to database: 10/16/2026, 17:51:05 UTC
Last enriched: 10/16/2026, 19:07:16 UTC
Last updated: 10/16/2026, 19:49:15 UTC
Views: 2
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.