Security readout for executives and security teams
Plain-English summary
DocsGPT 0.15.0 and earlier can process attacker-controlled custom prompts as server-side templates. An unauthenticated attacker may abuse this behavior to run code on the DocsGPT server, potentially stealing data, changing systems, or disrupting service.
Executive priority
Treat internet-accessible or otherwise untrusted-user-accessible deployments as an immediate remediation priority. Restrict access while confirming versions and awaiting or applying vendor-supported remediation. Investigate affected hosts if monitoring indicates unexpected server activity.
Technical view
The custom prompt feature renders user-supplied content through Jinja without sanitization or sandboxing. This creates server-side template injection classified as CWE-94. The supplied record reports network-reachable, low-complexity exploitation requiring neither authentication nor user interaction, with potential full confidentiality, integrity, and availability impact.
Likely exposure
Deployments running DocsGPT 0.15.0 or earlier are potentially affected, especially when unauthenticated users can reach custom-prompt chatbot functionality. The bundle provides no affected CPEs or deployment-specific configuration details, so exposure requires local confirmation.
Exploitation context
The supplied sources describe a path from unauthenticated template injection to remote code execution. CVSS 3.1 is 9.8. This CVE is not listed as KEV in the bundle, and no cited evidence establishes active exploitation in the wild.
Researcher notes
The central claim is unsanitized, unsandboxed Jinja rendering within custom prompts, enabling SSTI and reported RCE. The bundle identifies DocsGPT 0.15.0 and below, but its structured affected-product fields are unspecified. No official patch version, workaround, or exploitation telemetry is provided.
Mitigation direction
- Check DocsGPT vendor guidance for a fixed release or official mitigation, then apply it promptly.
- Until remediated, restrict network access to trusted users and systems.
- Disable the custom prompt feature if operationally feasible, pending vendor guidance.
- Monitor application hosts for unexpected process execution, file changes, or outbound connections.
Validation and detection
- Inventory deployments and confirm whether DocsGPT 0.15.0 or earlier is running.
- Determine whether unauthenticated users can reach custom-prompt chatbot functionality.
- Verify user prompts are not rendered through unsandboxed Jinja templates.
- Review logs for suspicious template-like input and anomalous server activity; avoid live exploit testing.
Public sources used
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
CWE-94: Code execution behavior lookup
Code execution and unsafe deserialization weaknesses often justify reviewing execution behavior and process telemetry. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Open ATT&CK lookupExecution behavior lookup
The CVE wording references code or command execution, so execution technique review may help defensive triage. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.
Open ATT&CK lookupCVE-2026-31020 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
Open ATT&CK lookup- Severity
- Critical
- CVSS
- 9.8 (3.1)
- Known Exploited
- No
- Published
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CNA and ADP enrichment extracted from CVE v5
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
SSVC decision data
CVSS vector scores
1 official scoreWe collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H3.95.9CISA-ADPVulnerability scoring details
Base CVSS 3.1 score
9.8CriticalVector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Vulnerability timeline
Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.
- CVE reservedCVE Program
The CVE ID was reserved by the assigning CNA.
- CVE publishedCVE Program
The CVE record was published.
- CVE updatedCVE Program
The CVE record metadata indicates this as the latest update time.
ADP provider summaries
Source materials
- CVE List V5 sourceCVE List V5
- https://github.com/PhDg1410/CVE/tree/main/CVE-2026-31020CVE reference, mitre
Products and packages named in the record
CWE details
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
Improper Control of Generation of Code ('Code Injection')
Improper Control of Generation of Code ('Code Injection') represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.