VulnTideExploited vulnerabilities, by vendor. Data as of .
Not in CISA KEVPublished CVSS 9.3 criticalEPSS 0.8% probability of exploitation in 30 days
eosphoros-ai

CVE-2026-77932: DB-GPT through 0.8.2 Unauthenticated RCE via /api/v1/chat/react-agent

Is it exploited?

Not on CISA's list. CISA has not added it to the Known Exploited Vulnerabilities catalog as of . If CISA adds it, this page shows it as known exploited.

How likely is exploitation in the next 30 days?
0.8%

EPSS score, percentile 56.6 of all scored records. A probability estimated by FIRST, not a report of exploitation.

CISA's SSVC assessment in the CVE record lists exploitation as poc.

How severe?
9.3 Critical

CVSS v4.0 base score, given by the CNA

What should I do?

CISA has set no required action, because the vulnerability is not in KEV.

The CVE record links no vendor advisory, patch or mitigation.

Which versions are affected?

Affected

  • 0.8.2 and earlier

Versions by product

Source: CISA Known Exploited Vulnerabilities (KEV) catalog, 2026.10.28, as of ; FIRST Exploit Prediction Scoring System (EPSS), v2026.06.15, as of ; CVE List V5 (CVE Program), cve_2026-10-29_0000Z, as of . About the data.

What to do

Advisories and patches

The CVE record links no vendor advisory, patch or mitigation.

Affected products and versions

As listed in the CVE record.

eosphoros-ai DB-GPT
StatusVersions
Affected0.8.2 and earlier

Versions not listed are: unaffected.

Source: CVE List V5 (CVE Program), cve_2026-10-29_0000Z, as of . About the data.

About this vulnerability

DB-GPT through 0.8.2 contains an unauthenticated remote code execution vulnerability because the /api/v1/chat/react-agent endpoint relies on a mock get_user_from_headers function that grants every caller the admin role. Unauthenticated attackers can send prompts that make the ReAct agent's unsandboxed code_interpreter and shell_interpreter tools run arbitrary Python or bash as root in the webserv…

Summary: CVE record, as of .

  • CISA has not added CVE-2026-77932 to its Known Exploited Vulnerabilities (KEV) catalog, as of 28 Oct 2026.
  • The CVE record was published on 20 Oct 2026.
  • The CVE record carries a CVSS v4.0 base score of 9.3 (Critical), given by its CNA.
  • FIRST's EPSS model puts the probability of exploitation in the next 30 days at 0.8% (percentile 56.6), as of 29 Oct 2026. EPSS is a statistical estimate, not a report of exploitation.
  • CISA's SSVC assessment in the CVE record: exploitation poc, automatable yes, technical impact total.

Source: CISA Known Exploited Vulnerabilities (KEV) catalog, 2026.10.28, as of ; CVE List V5 (CVE Program), cve_2026-10-29_0000Z, as of ; FIRST Exploit Prediction Scoring System (EPSS), v2026.06.15, as of . About the data.

Description

DB-GPT through 0.8.2 Unauthenticated RCE via /api/v1/chat/react-agent

DB-GPT through 0.8.2 contains an unauthenticated remote code execution vulnerability because the /api/v1/chat/react-agent endpoint relies on a mock get_user_from_headers function that grants every caller the admin role. Unauthenticated attackers can send prompts that make the ReAct agent's unsandboxed code_interpreter and shell_interpreter tools run arbitrary Python or bash as root in the webserver container, including reaching the bundled database with default credentials.

Source: CVE List V5 (CVE Program), cve_2026-10-29_0000Z, as of . About the data.

Weakness

CWE and CAPEC are maintained by MITRE; the entries are those named in the CVE record.

Timeline

DateEvent
CVE record published

References