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.
- Products
- Not specified
- Affected versions
- Not specified
- Fixed versions
- Not specified
- CVEs
- CVE-2026-54519
- Confirmed fixed CVEs
- Not specified
- Updated in this feed
- 3 Nov 2026, 08:35 UTC · Revision 1
Source evidence
AI Agent Automation: Missing ownership checks in memory APIs allow cross-user memory read and deletion
core-osv · Original sourcePublished 17 Sept 2026, 21:58 UTC
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.
osv:CVE-2026-54519
Complete source record
{
"id": "90aaa1bb9ae149c2df869cc84b08c22bfd67a23f4b8e753f7889146265993bda",
"url": "https://osv.dev/vulnerability/CVE-2026-54519",
"method": "structured",
"payload": {
"kind": "advisory",
"title": "AI Agent Automation: Missing ownership checks in memory APIs allow cross-user memory read and deletion",
"summary": "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.",
"evidence": "osv:CVE-2026-54519",
"products": [],
"severity": "high",
"structured": {
"id": "CVE-2026-54519",
"aliases": [
"CVE-2026-54519",
"GHSA-qv97-83w4-ff86"
],
"metrics": [
{
"type": "CVSS_V3",
"score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H"
}
],
"affected": [
{
"ranges": [
{
"repo": "https://github.com/vmdeshpande/ai-agent-automation",
"type": "GIT",
"events": [
{
"introduced": "0"
},
{
"fixed": "3f589293b67ab90193406781ec9e7cdc5146a254"
},
{
"fixed": "96b31c216f6f670e64584f3623c07ac54461e703"
}
],
"database_specific": {
"extracted_events": [
{
"range": [
{
"introduced": "0"
},
{
"fixed": "0.9.1"
}
],
"source": "AFFECTED_FIELD",
"strategy": "StringRangeExpression"
},
{
"range": [
{
"fixed": "96b31c216f6f670e64584f3623c07ac54461e703"
}
],
"source": "REFERENCES_COMMIT"
},
{
"range": [
{
"fixed": "3f589293b67ab90193406781ec9e7cdc5146a254"
}
],
"source": "REFERENCES_TAG",
"original_tag": "v0.9.1"
}
]
}
}
],
"versions": [
"v0.9.0",
"v0.8.0",
"v0.7.0",
"v0.6.0",
"v0.5.1",
"v0.5.0",
"v0.4.0",
"v0.3.0",
"v0.2.0",
"v0.1.0"
],
"database_specific": {
"source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-54519.json"
}
}
],
"modified": "2026-10-28T02:30:27.427924105Z",
"provider": "osv",
"references": [
"https://github.com/vmDeshpande/ai-agent-automation/releases/tag/v0.9.1",
"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/54xxx/CVE-2026-54519.json",
"https://github.com/vmDeshpande/ai-agent-automation/security/advisories/GHSA-qv97-83w4-ff86",
"https://nvd.nist.gov/vuln/detail/CVE-2026-54519",
"https://github.com/vmDeshpande/ai-agent-automation/commit/96b31c216f6f670e64584f3623c07ac54461e703"
],
"provider_metadata": {
"cwe_ids": [
"CWE-862"
],
"cna_assigner": "GitHub_M",
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/54xxx/CVE-2026-54519.json"
}
},
"related_cves": [
{
"value": "CVE-2026-54519",
"evidence": "/id"
}
],
"security_relevant": true,
"severity_evidence": "/severity/0/score"
},
"source_id": "core-osv",
"document_id": 493868,
"published_at": "2026-09-17T21:58:41.375+00:00"
}