vmDeshpande ai-agent-automation
AI Agent Automation: Missing ownership checks in memory APIs allow cross-user memory read and deletion
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.
Affected versions and mitigation
From the CVE record and the vendor's references.Affected
- < 0.9.1
Fixed in 0.9.1
Mitigation
Upgrade ai-agent-automation to 0.9.1 or later.
References
- Vendor advisory github.com/vmDeshpande/ai-agent-automation/sec…
- Patch github.com/vmDeshpande/ai-agent-automation/com…
- Release notes github.com/vmDeshpande/ai-agent-automation/rel…
Timeline
Days relative to CVE publicationNo public PoC found yet; not in CISA KEV.
PoC repositories
Found on GitHub.1 informational
Informational 1
| Repository | Created | Stars | Assessment |
|---|---|---|---|
| chaitanyagarware/CVE-2026-54519 | 9 Jul 2026 −71 d | 1 | Informational · write-up |
Only PoCs count toward the first-PoC date and the characteristics below. Do not run PoC code from unknown sources.