CVE-2026-54519

HIGHPre-NVD 8.88.8—
EchelonGraph scoreMEDIUM confidence

This high-severity CVE scores 8.8 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.5%, top 59% of all CVEs by exploit prediction. GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).

Triggered by: NVD CVSS baseline
Sources: epss, secondary
Elevated
8.8EG
EchelonGraph verdictPlan a fixSerious severity, but no confirmed exploitation yet.
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 1%CVSS: 8.8Exploit: Elevated riskExposed: 0

No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.

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
8.8
EG Score
8.8(medium)
EG Risk
56(Track*)
EG Risk 56/100SSVC: Track*

EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).

How it’s computed
Severity88% × 45%
Exploitation40% × 40%
Automatability0% × 15%
Action: Watch closely — could escalate to Attend.
EPSS PROB
1%
EPSS %ILE
41%
KEV
Not listed

Published

September 17, 2026

Last Modified

September 24, 2026

Advisory Details (3)

Auto-updated Sep 17, 2026
🔬 Proof of concept available. Patch available. Sources: github_commit, github_release, github.
github Patch Available🟡 PoC Available

Missing ownership checks in memory APIs allow cross-user memory read and deletion · Advisory · vmDeshpande/ai-agent-automation · GitHub

https://github.com/vmDeshpande/ai-agent-automation/security/advisories/GHSA-qv97-83w4-ff86
github_release Patch Available

v0.9.1 - Security Update

Patch available: vmDeshpande/ai-agent-automation v0.9.1

https://github.com/vmDeshpande/ai-agent-automation/releases/tag/v0.9.1
github_commit Patch Available

commit 96b31c216f6f (vmDeshpande/ai-agent-automation)

Patch available: vmDeshpande/ai-agent-automation v0.9.1 (contains commit 96b31c216f6f)

https://github.com/vmDeshpande/ai-agent-automation/commit/96b31c216f6f670e64584f3623c07ac54461e703

Weakness Classification(1)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 13× in last 7d / 16× in last 30d)

Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.

  1. 2026-09-24 21:39 UTCEG score recompute
  2. 2026-09-24 14:04 UTCEPSS rescore
  3. 2026-09-24 01:18 UTCEG score recompute
  4. 2026-09-23 17:54 UTCEPSS rescore
  5. 2026-09-23 01:54 UTCEG score recompute
  6. 2026-09-22 14:11 UTCEG score recompute
  7. 2026-09-22 02:29 UTCEG score recompute
  8. 2026-09-22 02:01 UTCEG score recompute
  9. 2026-09-20 20:38 UTCEG score recompute
  10. 2026-09-20 20:16 UTCEPSS rescore
  11. 2026-09-19 21:14 UTCEG score recompute
  12. 2026-09-18 21:46 UTCEG score recompute
  13. 2026-09-18 19:28 UTCEPSS rescore
  14. 2026-09-17 22:23 UTCEG score recompute
  15. 2026-09-17 22:09 UTCEG score recompute
  16. 2026-09-17 22:09 UTCMITRE cvelistV5first tracked

Related CVEs(same CWE)

Frequently asked(5)

What is CVE-2026-54519?
CVE-2026-54519 is a high vulnerability published on September 17, 2026. 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…
When was CVE-2026-54519 disclosed?
CVE-2026-54519 was first published in the National Vulnerability Database on September 17, 2026, with the most recent update on September 24, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-54519 actively exploited?
CVE-2026-54519 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 1% probability of exploitation in the next 30 days, which ranks it in the top 58.7% of all scored CVEs.
What is the CVSS score of CVE-2026-54519?
CVE-2026-54519 has a CVSS v3 base score of 8.8 (NVD).
How do I remediate CVE-2026-54519?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2026-54519, EchelonGraph cross-links them in the Vendor Advisories panel below — those typically contain the canonical remediation steps, fixed version numbers, and any vendor-specific mitigations.

Dependency Blast Radius

Explore the affected products and dependency analysis for CVE-2026-54519

Explore →

Is Your Infrastructure Affected by CVE-2026-54519?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.

Book a Demo →Browse All CVEs