CVE-2026-5631

HIGHNVD 7.37.3
EchelonGraph scoreMEDIUM confidence

“—” beside the score: it is equal to NVD's CVSS score.

Score 7.3 from GitHub Security Advisory published 2026-04-06. NVD baseline CVSS 7.3; sources differ by 0.0.

Triggered by: GitHub Security Advisory CVSS
Sources: EPSS, GitHub Security Advisory, NVD CVSS v3
Trending — 4 sources updated this weekElevated
7.3EG
EchelonGraph verdictPlan mitigationRemediate within your standard update timelines at low or medium mission impact and sooner than that at high (the SSVC decision on this page).
  • CISA's Vulnrichment rates exploitation as PoC; EchelonGraph holds no exploit-code reference for it
CISA-KEV: Not listedEPSS PROB: 0.5%CVSS: 7.3Exploit: No code on recordExposed services: Not assessed

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

The CVE record's description, written by its CNA (VulDB), states the affected versions: "A vulnerability has been found in assafelovic gpt-researcher up to 3.4.3." No release containing a fix is confirmed on record.

A vulnerability has been found in assafelovic gpt-researcher up to 3.4.3. This affects the function extract_command_data of the file backend/server/server_utils.py of the component ws Endpoint. Such manipulation of the argument args leads to code injection. The attack may be performed from remote. The exploit has been disclosed to the public and may be used. The project was informed of the problem early through an issue report but has not responded yet.

CVSS v3
7.3
EG Score
7.3HIGHmedium confidence
EG Risk
64
EG Risk 64/100

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 (value × EchelonGraph’s weight)
Severity73% × 45%
The EG Score, 7.3 of 10.
Exploitation40% × 40%
EchelonGraph's fixed weight for EG-KEV Tier 3 (Elevated): a constant, not a probability.
Automatability100% × 15%
CISA's SSVC Automatable value: yes (Vulnrichment).
SSVC (CISA's decision table, applied by EchelonGraph): Track at low or medium mission impact; Attend at high (mission-essential systems).
Exploitation public PoC (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE.
Action: No fix is confirmed yet. Restrict network exposure of the affected system within your standard update timelines at low or medium mission impact and sooner than that at high, and watch for a fix.
EPSS PROB
0.5%
EPSS %ILE
42nd
KEV
Not listed

SSVC (CISA's decision table, applied by EchelonGraph)Track at low or medium mission impact; Attend at high (mission-essential systems).

No fix is confirmed yet. Restrict network exposure of the affected system within your standard update timelines at low or medium mission impact and sooner than that at high, and watch for a fix.

Exploitation public PoC (CISA Vulnrichment) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE. Mission impact is CISA's Mission & Well-being decision point, and only you can judge it. CISA's table makes it high when Mission Prevalence is Essential — the vulnerable component "directly provides capabilities that constitute at least one MEF for at least one entity" (MEF: mission essential function) — or when Public Well-Being Impact is Irreversible: "multiple fatalities are likely", the cyber-physical system "is likely lost or destroyed", "extreme or serious externalities" are imposed on other parties, or social systems such as elections or the financial grid "are destabilized and potentially collapse". CISA's decision table

BOD 26-04 (CISA's remediation timeline, Table 1)14 days if the affected system is publicly exposed; 60 days if it is not.

In CISA KEV no (CISA's KEV catalog) · Automatable yes (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). Whether your system is publicly exposed is yours to answer. BOD 26-04 binds US Federal Civilian Executive Branch agencies; for anyone else it is CISA's published timeline, a reference rather than an obligation. The directive · how EchelonGraph applies it

Published

April 6, 2026

Last Modified

July 24, 2026

Advisory Details (2)

Auto-updated Jul 24, 2026
No fix on record yet.
Web page

Unauthenticated Remote Code Execution via MCP Command Injection in gpt-researcher · Issue #1694 · assafelovic/gpt-researcher · GitHub

https://github.com/assafelovic/gpt-researcher/issues/1694
Web page

GitHub - assafelovic/gpt-researcher: An autonomous agent that conducts deep research on any data using any LLM providers · GitHub

https://github.com/assafelovic/gpt-researcher/

Weakness Classification(2)

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

Data Freshness Timeline

(refreshed 14× in last 7d / 32× in last 30d)

Each row is a time one of our pipelines fetched, updated or re-scored this CVE. 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. An arrow marks a change the record states ("CVSS v3 → 9.1"); EPSS and GHSA rows show the values recorded at that time, not what changed (EPSS values are rounded; hover one for the exact figures). Most recent first.

Showing the most recent 100 of 211 refreshes on record for this CVE.

A repeat, a row identical to one the same pipeline wrote less than 10 seconds earlier, is not a separate refresh and is not counted. None are among the latest 100 rows. The 111 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-10-17 03:01 UTCEG score recompute
  2. 2026-10-17 03:01 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  3. 2026-10-16 16:43 UTCEPSS rescoreEPSS 0.5% · 42nd percentile
  4. 2026-10-15 16:32 UTCEPSS rescoreEPSS 0.5% · 42nd percentile
  5. 2026-10-14 16:33 UTCEPSS rescoreEPSS 0.5% · 42nd percentile
  6. 2026-10-13 16:34 UTCEPSS rescoreEPSS 0.5% · 42nd percentile
  7. 2026-10-12 16:34 UTCEPSS rescoreEPSS 0.5% · 42nd percentile
  8. 2026-10-12 15:55 UTCEG score recompute
  9. 2026-10-11 19:38 UTCEG score recompute
  10. 2026-10-11 16:53 UTCEG score recompute
  11. 2026-10-11 14:16 UTCEG score recompute
  12. 2026-10-11 13:49 UTCEPSS rescoreEPSS 0.5% · 42nd percentile
  13. 2026-10-11 00:22 UTCOSV refresh
  14. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.5% · 42nd percentile
  15. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.5% · 42nd percentile
  16. 2026-10-08 17:13 UTCEPSS rescoreEPSS 0.5% · 42nd percentile
  17. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.5% · 42nd percentile
  18. 2026-10-06 15:18 UTCEPSS rescoreEPSS 0.5% · 42nd percentile
  19. 2026-10-05 17:43 UTCEPSS rescoreEPSS 0.5% · 41st percentile
  20. 2026-10-04 23:22 UTCEPSS rescoreEPSS 0.5% · 41st percentile
  21. 2026-10-03 14:26 UTCEPSS rescoreEPSS 0.5% · 41st percentile
  22. 2026-10-02 17:56 UTCEPSS rescoreEPSS 0.5% · 41st percentile
  23. 2026-10-01 19:50 UTCEPSS rescoreEPSS 0.5% · 41st percentile
  24. 2026-09-30 15:03 UTCEPSS rescoreEPSS 0.5% · 41st percentile
  25. 2026-09-28 13:51 UTCEPSS rescoreEPSS 0.5% · 41st percentile
Show 75 more
  1. 2026-09-26 15:59 UTCEPSS rescoreEPSS 0.5% · 41st percentile
  2. 2026-09-24 14:04 UTCEPSS rescoreEPSS 0.5% · 41st percentile
  3. 2026-09-23 17:54 UTCEPSS rescoreEPSS 0.3% · 24th percentile
  4. 2026-09-21 12:19 UTCOSV refresh
  5. 2026-09-20 20:16 UTCEPSS rescoreEPSS 0.3% · 24th percentile
  6. 2026-09-18 19:28 UTCEPSS rescoreEPSS 0.3% · 24th percentile
  7. 2026-09-17 19:31 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  8. 2026-09-16 14:08 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  9. 2026-09-16 05:15 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  10. 2026-09-15 03:11 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  11. 2026-09-13 16:47 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  12. 2026-09-11 14:53 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  13. 2026-09-10 09:35 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  14. 2026-09-08 22:01 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  15. 2026-09-06 13:47 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  16. 2026-09-04 05:07 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  17. 2026-09-02 14:12 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  18. 2026-09-02 09:44 UTCOSV refresh
  19. 2026-09-01 13:54 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  20. 2026-09-01 04:40 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  21. 2026-08-30 19:17 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  22. 2026-08-30 01:22 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  23. 2026-08-28 21:42 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  24. 2026-08-27 14:25 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  25. 2026-08-26 14:46 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  26. 2026-08-25 13:49 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  27. 2026-08-23 00:19 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  28. 2026-08-21 23:49 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  29. 2026-08-20 22:55 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  30. 2026-08-19 17:04 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  31. 2026-08-18 13:48 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  32. 2026-08-17 13:47 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  33. 2026-08-16 14:56 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  34. 2026-08-16 08:27 UTCEG score recompute
  35. 2026-08-16 08:27 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  36. 2026-08-15 01:30 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  37. 2026-08-14 16:24 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  38. 2026-08-14 05:35 UTCEG score recompute
  39. 2026-08-14 05:35 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  40. 2026-08-13 22:00 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  41. 2026-08-13 09:46 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  42. 2026-08-12 19:50 UTCEG score recompute
  43. 2026-08-12 19:50 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  44. 2026-08-12 13:51 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  45. 2026-08-11 20:10 UTCEG score recompute
  46. 2026-08-11 20:10 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  47. 2026-08-11 03:20 UTCEG score recompute
  48. 2026-08-11 03:20 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  49. 2026-08-11 00:00 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  50. 2026-08-10 02:50 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  51. 2026-08-09 15:55 UTCEG score recompute
  52. 2026-08-09 15:55 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  53. 2026-08-09 13:46 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  54. 2026-08-09 05:06 UTCEG score recompute
  55. 2026-08-09 05:06 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  56. 2026-08-08 16:37 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  57. 2026-08-08 02:01 UTCEG score recompute
  58. 2026-08-08 02:01 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  59. 2026-08-07 15:11 UTCEG score recompute
  60. 2026-08-07 15:11 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  61. 2026-08-06 13:47 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  62. 2026-08-06 13:04 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  63. 2026-08-06 00:10 UTCEG score recompute
  64. 2026-08-06 00:10 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  65. 2026-08-05 19:17 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  66. 2026-08-04 15:10 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  67. 2026-08-04 10:39 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  68. 2026-08-03 22:31 UTCEG score recompute
  69. 2026-08-03 22:31 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  70. 2026-08-03 10:36 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  71. 2026-08-03 01:17 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  72. 2026-08-02 14:27 UTCEG score recompute
  73. 2026-08-02 14:27 UTCGHSA enrichmentGHSA-2q6q-x2rq-67q4 · GitHub CVSS 7.3
  74. 2026-08-01 04:16 UTCEPSS rescoreEPSS 0.3% · 23rd percentile
  75. 2026-07-30 16:28 UTCEPSS rescoreEPSS 0.3% · 23rd percentile

Related CVEs(same CWE)

Frequently asked(5)

What is CVE-2026-5631?
CVE-2026-5631 is a high-severity vulnerability; its CVE record was published on April 6, 2026. A vulnerability has been found in assafelovic gpt-researcher up to 3.4.3. This affects the function extractcommanddata of the file backend/server/server_utils.py of the component ws Endpoint. Such manipulation of the argument args leads to code injection. The attack may be performed from remote.…
When was the CVE record for CVE-2026-5631 published?
The CVE record for CVE-2026-5631 was published on April 6, 2026. That is the record's publication date; the vulnerability itself may have been made public earlier. EchelonGraph's copy of the record carries a last-modified date of July 24, 2026; the record at its source may have been updated since.
Is CVE-2026-5631 actively exploited?
CVE-2026-5631 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.5% probability of exploitation in the next 30 days (42nd percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-5631?
CVE-2026-5631 has a CVSS v3 base score of 7.3 (NVD).
How do I remediate CVE-2026-5631?
No fix for CVE-2026-5631 is confirmed yet. Until one is published, restrict network exposure of the affected system — for example, keep it off the internet or limit it to trusted networks — and watch for a fix. The CVE record's description, written by its CNA (VulDB), states the affected versions: "A vulnerability has been found in assafelovic gpt-researcher up to 3.4.3." No release containing a fix is confirmed on record.

Dependency Blast Radius

Explore the affected products and dependency analysis for CVE-2026-5631

Explore →

Is Your Infrastructure Affected by CVE-2026-5631?

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

Book a Demo →Browse All CVEs