CVE-2025-32394

MEDIUMPre-NVD 5.35.3—
EchelonGraph scoreMEDIUM confidence

This medium-severity CVE scores 5.3 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.2%, top 84% 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
5.3
EchelonGraph verdictMonitorLow exploitation likelihood right now — keep watching.
  • Lower severity and no public exploit yet
CISA-KEV: Not listedEPSS: 0%CVSS: 5.3Exploit: NoneExposed: 0

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

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.32, there is a DoS vulnerability in AITextSummarizerBlock. Malicious users can amplify their input. For example, if a malicious user inputs 10K of content, the server will consume 50G of memory, eventually causing memory resources to be exhausted, resulting in DoS. This vulnerability is fixed in 0.6.32.

CVSS v3
5.3
EG Score
5.3(medium)
EPSS
15.8%
KEV
Not listed

Published

June 26, 2026

Last Modified

June 27, 2026

Advisory Details (1)

Auto-updated Jun 26, 2026
🔬 Proof of concept available. Patch available. Sources: github.
github Patch Available🟡 PoC Available

Quadratic memory amplification in AITextSummarizerBlock chunking (DoS via attacker-controlled max_tokens/overlap) · Advisory · Significant-Gravitas/AutoGPT · GitHub

https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-955p-gpfx-r66j

Weakness Classification(2)

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

Data Freshness Timeline

(refreshed 16× in last 7d / 34× 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. 2026-07-11 08:27 UTCEPSS rescore
  2. 2026-07-11 08:27 UTCEPSS rescore
  3. 2026-07-11 06:39 UTCEG score recompute
  4. 2026-07-10 05:44 UTCEG score recompute
  5. 2026-07-09 19:09 UTCEPSS rescore
  6. 2026-07-09 04:50 UTCEG score recompute
  7. 2026-07-08 15:14 UTCEPSS rescore
  8. 2026-07-08 03:57 UTCEG score recompute
  9. 2026-07-07 13:45 UTCEPSS rescore
  10. 2026-07-07 03:03 UTCEG score recompute
  11. 2026-07-06 16:27 UTCEPSS rescore
  12. 2026-07-06 16:26 UTCEPSS rescore
  13. 2026-07-06 02:22 UTCEPSS rescore
  14. 2026-07-06 02:08 UTCEG score recompute
  15. 2026-07-05 02:30 UTCEPSS rescore
  16. 2026-07-05 01:15 UTCEG score recompute
  17. 2026-07-04 00:06 UTCEG score recompute
  18. 2026-07-02 23:13 UTCEG score recompute
  19. 2026-07-02 17:01 UTCEPSS rescore
  20. 2026-07-01 22:19 UTCEG score recompute
  21. 2026-07-01 15:06 UTCEPSS rescore
  22. 2026-06-30 23:22 UTCEPSS rescore
  23. 2026-06-30 23:21 UTCEPSS rescore
  24. 2026-06-30 21:18 UTCEG score recompute
  25. 2026-06-29 20:22 UTCEG score recompute
Show 9 more
  1. 2026-06-29 14:06 UTCEPSS rescore
  2. 2026-06-28 19:29 UTCEG score recompute
  3. 2026-06-28 14:07 UTCEPSS rescore
  4. 2026-06-28 14:07 UTCEPSS rescore
  5. 2026-06-28 04:55 UTCEPSS rescore
  6. 2026-06-28 04:55 UTCEPSS rescore
  7. 2026-06-27 18:35 UTCEG score recompute
  8. 2026-06-26 17:41 UTCEG score recompute
  9. 2026-06-26 17:41 UTCNVD updatefirst tracked

Frequently asked(5)

What is CVE-2025-32394?
CVE-2025-32394 is a medium vulnerability published on June 26, 2026. AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.32, there is a DoS vulnerability in AITextSummarizerBlock. Malicious users can amplify their input. For example, if a malicious user inputs 10K of content, the…
When was CVE-2025-32394 disclosed?
CVE-2025-32394 was first published in the National Vulnerability Database on June 26, 2026, with the most recent update on June 27, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2025-32394 actively exploited?
CVE-2025-32394 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 15.8% percentile likelihood of exploitation in the next 30 days — higher percentiles indicate greater predicted risk.
What is the CVSS score of CVE-2025-32394?
CVE-2025-32394 has a CVSS v3 base score of 5.3 (NVD).
How do I remediate CVE-2025-32394?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2025-32394, 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-2025-32394

Explore →

Is Your Infrastructure Affected by CVE-2025-32394?

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

Start Free Scan →Browse All CVEs