Skip to main content

CVE-2026-54519: CWE-862: Missing Authorization in vmDeshpande ai-agent-automation

0
High
VulnerabilityCVE-2026-54519cvecve-2026-54519cwe-862
Published: 09/17/2026 (09/17/2026, 21:58:41 UTC)
Source: CVE Database V5
Vendor/Project: vmDeshpande
Product: ai-agent-automation

Description

AI Agent Automation is a modular AI agent workflow automation platform with schedulers, tools, and observability. Prior to 0.9.1, backend/src/controllers/memory.controller.js authenticates requests but listMemories, deleteMemory, and clearAgentMemory use a caller-supplied agentId or memory _id without verifying through the related Agent that the record belongs to req.user. An authenticated attacker who knows or obtains another user's identifiers can read victim AgentMemory content, including conversation history, agent context, task data, embeddings, and metadata, delete an individual victim memory, or clear all memory belonging to a victim agent. This breaks tenant isolation and causes unauthorized disclosure and data loss. This issue is fixed in version 0.9.1.

CVSS v3.1

Score 8.8high

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

Affected software

vmDeshpande

ai-agent-automation

Affected versions
<0.9.1
GitHub Actionsmore threats →ai
vmdeshpande/ai-agent-automation
pkg:github/vmdeshpande/ai-agent-automation
Affected versions
<0.9.1

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

AILast updated: 09/17/2026, 22:31:44 UTC

Technical Analysis

The vulnerability in vmDeshpande ai-agent-automation (before version 0.9.1) exists because the backend memory controller functions (listMemories, deleteMemory, clearAgentMemory) use caller-supplied agentId or memory _id parameters without verifying that these records belong to the authenticated user (req.user). This missing authorization check (CWE-862) enables an authenticated attacker who knows or obtains another user's identifiers to read sensitive AgentMemory content (conversation history, agent context, task data, embeddings, metadata), delete individual memories, or clear all memories of a victim agent. This breaks tenant isolation and leads to confidentiality and integrity violations. The vulnerability has a CVSS 3.1 score of 8.8 (high severity) and was fixed in version 0.9.1.

Potential Impact

An authenticated attacker can bypass authorization controls to access or delete another user's agent memory data, resulting in unauthorized disclosure of sensitive information and data loss. This compromises tenant isolation, confidentiality, integrity, and availability of agent memory data within the affected platform.

Mitigation Recommendations

Upgrade to version 0.9.1 or later, where this missing authorization vulnerability is fixed. No other mitigation is required as the vendor has provided an official fix.

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
GitHub_M
Date Reserved
2026-06-15T18:40:01.650Z
Cvss Version
3.1
State
PUBLISHED

Threat ID: 6aac671555bf5e2cf5ffd688

Added to database: 09/17/2026, 22:17:57 UTC

Last enriched: 09/17/2026, 22:31:44 UTC

Last updated: 09/18/2026, 02:12:50 UTC

Views: 7

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