Security readout for executives and security teams
Plain-English summary
CVE-2025-65720 is a reported critical command-execution issue in Open Source GPT Researcher v3.3.7. The record says a crafted HTML page can lead to arbitrary commands on a victim system. For executives, treat exposed AI research tooling as a high-impact business risk until vendor status is confirmed.
Executive priority
Prioritize immediate exposure discovery and containment. The potential impact is full system compromise, but public evidence lacks confirmed exploitation and clear vendor remediation details.
Technical view
The CVE describes arbitrary command execution in GPT Researcher v3.3.7, classified as CWE-77 with CVSS 3.1 score 9.8. Published affected-product metadata is sparse, listing vendor and product as n/a, but the title and references identify GPT Researcher. The description mentions user interaction; the CVSS vector lists UI:N, so evidence is inconsistent.
Likely exposure
Likely exposure is limited to organizations running or testing GPT Researcher v3.3.7, especially in workflows that process untrusted web or HTML content. Public CPE and affected-product metadata are incomplete, so asset confirmation is required before scoping risk.
Exploitation context
The supplied record does not show CISA KEV listing or active exploitation evidence. The CVE description states exploitation involves a crafted HTML page, but the CVSS vector indicates no user interaction, which should be treated as an unresolved source inconsistency.
Researcher notes
Focus research on reconciling the interaction discrepancy between the CVE description and CVSS vector. Avoid assuming all GPT Researcher versions are affected; the supplied evidence names v3.3.7 only.
Mitigation direction
- Inventory GPT Researcher deployments and identify any v3.3.7 instances.
- Check the project repository and vendor advisories for fixed versions or official mitigations.
- Isolate affected deployments from untrusted HTML or web content until guidance is confirmed.
- Restrict runtime privileges and network access for GPT Researcher processes.
- Monitor for unexpected child processes or command execution from the application context.
Validation and detection
- Confirm installed GPT Researcher versions across developer, server, and agent environments.
- Review whether any deployment processes untrusted HTML or externally supplied web content.
- Check logs for unusual process spawning from GPT Researcher runtimes.
- Track the CVE record and referenced advisories for affected-version and patch updates.
- Document any compensating controls applied while awaiting confirmed vendor remediation.
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-77: Command execution behavior lookup
Command injection weaknesses can lead defenders to review execution techniques and command interpreter 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 lookupCVE-2025-65720 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/assafelovic/gpt-researcherCVE reference, mitre
- https://www.ox.security/blog/gpt-researcher-remote-code-executionCVE reference, mitre
- https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem/CVE 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.