Skip to main content
EPSS 0.3%top 75%

CVE-2026-10105: CWE-89 Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection') in agno-agi agno

0
High
VulnerabilityCVE-2026-10105cvecve-2026-10105cwe-89
Published: 05/29/2026 (05/29/2026, 16:18:19 UTC)
Source: CVE Database V5
Vendor/Project: agno-agi
Product: agno

Description

agno 2.6.5 contains a SQL injection vulnerability in the ClickHouse vector database backend that allows attackers to inject arbitrary SQL expressions by supplying malicious metadata keys and values to the delete_by_metadata() method. Attackers can exploit the unsafe f-string interpolation in clickhousedb.py to delete all rows, target specific rows, or extract information through error-based or blind SQL injection techniques.

CVSS v3.1

Score 8.3high

Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
Low
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:L

Affected software

agno-agi

agno

Affected versions
>=0 <=2.6.5=0

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 08/15/2026, 13:43:30 UTC

Technical Analysis

agno 2.6.5 is affected by a SQL injection vulnerability (CWE-89) in the ClickHouse vector database backend. The issue is due to unsafe f-string interpolation in the clickhousedb.py file within the delete_by_metadata() method, which processes metadata keys and values without proper neutralization. This allows attackers with limited privileges (PR:L) to inject arbitrary SQL commands remotely (AV:N) without user interaction (UI:N). The vulnerability impacts confidentiality and integrity at a high level and availability at a low level (CVSS 8.3). No vendor advisory or patch information is available to confirm remediation status.

Potential Impact

Successful exploitation can allow an attacker to delete all or specific rows in the database or extract sensitive information via error-based or blind SQL injection. This compromises data confidentiality and integrity, with a lesser impact on availability. The attack requires low complexity and limited privileges but no user interaction.

Mitigation Recommendations

Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, avoid using the vulnerable delete_by_metadata() method with untrusted input. Implement input validation and sanitization as a temporary measure if possible.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
VulnCheck
Date Reserved
2026-05-29T16:02:26.062Z
Cvss Version
3.1
State
PUBLISHED

Threat ID: 6a19cdf2e29bf47b50fb46ee

Added to database: 05/29/2026, 17:33:38 UTC

Last enriched: 08/15/2026, 13:43:30 UTC

Last updated: 09/12/2026, 22:01:31 UTC

Views: 91

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

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

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses