CVE-2026-45374

CRITICALNVD 9.69.6
EchelonGraph scoreMEDIUM confidence

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

This critical-severity CVE scores 9.6 under NVD CVSS v3. EPSS exploit probability: 0.5% (38th percentile of EPSS-scored CVEs). No GitHub Security Advisory CVSS is on record for this CVE.

Triggered by: Headline CVSS from NVD CVSS v3
Sources: EPSS, NVD CVSS v3
Elevated
9.6EG
EchelonGraph verdictPlan a fixRemediate 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: 9.6Exploit: No code on recordExposed services: Not assessed

A fix is available — apply it.

CodeWhale is a DeepSeek + MiMo coding agent in terminal. Prior to 0.8.26, the task_create tool spawns durable sub-agents that inherit two insecure defaults, allow_shell defaults to true (config.rs:1499: self.allow_shell.unwrap_or(true)) and auto_approve defaults to true (task_manager.rs:297: auto_approve: Some(true)). When a user approves a task_create call (which requires ApprovalRequirement::Required), they approve what appears to be a benign work prompt. However, the spawned sub-agent silently receives unrestricted, unapproved shell access. This vulnerability is fixed in 0.8.26.

CVSS v3
9.6
EG Score
9.6CRITICALmedium confidence
EG Risk
59
EG Risk 59/100

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)
Severity96% × 45%
The EG Score, 9.6 of 10.
Exploitation40% × 40%
EchelonGraph's fixed weight for EG-KEV Tier 3 (Elevated): a constant, not a probability.
Automatability0% × 15%
CISA's SSVC Automatable value: no (Vulnrichment).
SSVC (CISA's decision table, applied by EchelonGraph): Track at low, Track* at medium and Attend at high mission impact.
Exploitation public PoC (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact total (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: A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high.
EPSS PROB
0.5%
EPSS %ILE
38th
KEV
Not listed

SSVC (CISA's decision table, applied by EchelonGraph)Track at low, Track* at medium and Attend at high mission impact.

A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high.

Exploitation public PoC (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact total (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; Fix on system upgrade if it is not.

In CISA KEV no (CISA's KEV catalog) · Automatable no (CISA Vulnrichment) · Technical impact total (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

May 28, 2026

Last Modified

May 30, 2026

Advisory Details (2)

Auto-updated Oct 2, 2026
Patch available. Sources: github_release, github.
GitHub advisoryMentions a patch (unverified)

task_create Insecure Defaults Enable RCE via Prompt Injection in Project Files · Advisory · Hmbown/Codewhale · GitHub

https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-72w5-pf8h-xfp4
GitHub release Patch Available

v0.8.26

Patch available: Hmbown/DeepSeek-TUI v0.8.26

https://github.com/Hmbown/DeepSeek-TUI/releases/tag/v0.8.26

Vendor Advisories for CVE-2026-45374(1)

These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.

Affected Packages

(1 across 1 ecosystem)
crates.io(1)
PackageVulnerable rangeFix by version rangeDependents
deepseek-tui—
  • every version up to 0.8.26: fixed in 0.8.26
—

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 16× 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 178 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 78 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

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

Related CVEs(same product + same CWE)

Frequently asked(5)

What is CVE-2026-45374?
CVE-2026-45374 is a critical-severity vulnerability; its CVE record was published on May 28, 2026. CodeWhale is a DeepSeek + MiMo coding agent in terminal. Prior to 0.8.26, the taskcreate tool spawns durable sub-agents that inherit two insecure defaults, allowshell defaults to true (config.rs:1499: self.allowshell.unwrapor(true)) and autoapprove defaults to true (taskmanager.rs:297: autoapprove:…
When was the CVE record for CVE-2026-45374 published?
The CVE record for CVE-2026-45374 was published on May 28, 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 May 30, 2026; the record at its source may have been updated since.
Is CVE-2026-45374 actively exploited?
CVE-2026-45374 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.5% probability of exploitation in the next 30 days (38th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-45374?
CVE-2026-45374 has a CVSS v3 base score of 9.6 (NVD).
How do I remediate CVE-2026-45374?
A fix for CVE-2026-45374 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-45374 are linked in the Vendor Advisories panel on this page.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-45374

Explore →

Is Your Infrastructure Affected by CVE-2026-45374?

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

Book a Demo →Browse All CVEs