CVE-2026-54519 AI Agent Automation: Missing ownership checks in memory APIs allow cross-user memory read and deletion
An authenticated attacker can read or delete other users' AI agent memory data due to missing ownership checks in the API.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-54519?
CVE-2026-54519 is a high-severity missing authorization vulnerability in vmDeshpande ai-agent-automation, published on 17 Sep 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official 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.
Weakness: CWE-862
Which versions are affected by CVE-2026-54519?
How do I fix CVE-2026-54519?
No fix has been published for CVE-2026-54519 yet. Limit exposure of the affected software until one is available.
Upgrade, and check permissions on every request on the server, not only in the interface. More about Missing authorization.
Is CVE-2026-54519 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-54519 exists.
Public exploit code: 1 proofs of concept on GitHub.
Sources
Also known as GHSA-qv97-83w4-ff86.