HighVulnerabilityLLM-specific

CVE-2026-66027: Suna broken access control in message queue API allows cross-user access

Source: NVD(opens in a new tab)
Identifier: CVE-2026-66027
Published: July 24, 2026
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.5%

Summary

Suna before 0.9.102 has a broken access control flaw in its message queue API. Authenticated attackers can read other users' pending prompt queues, read or delete their sessions, and inject prompts into another user's session queue, which the background drainer forwards to the victim's running AI agent with the victim's credentials and permissions.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 8.3(high)
CVSS vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:L
Attack vector: network
Attack complexity: low
Privileges required: low
User interaction: none
EPSS: 0.5%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 12, 2026.
Disclosure date: July 24, 2026

Weaknesses and techniques

Weakness (CWE): CWE-862
Attack pattern (CAPEC): CAPEC-122
AI threat technique (MITRE ATLAS): AML.T0051

Classification

Attack type: Prompt injection,
Other
Attack sophistication: Trivial
AI component targeted: Agent
Impact: Confidentiality,
Integrity
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-66027

First tracked: July 24, 2026 at 02:08 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 90% (self-assessed)

Summary

Mitigation

Related items