CVE-2026-54769

CRITICALPre-NVD 10.010.0
EchelonGraph scoreMEDIUM confidence

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

This critical-severity CVE scores 10.0 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.9% (59th percentile of EPSS-scored CVEs). No GitHub Security Advisory CVSS is on record for this CVE.

Triggered by: Headline CVSS from a secondary CVSS source
Sources: EPSS, a secondary CVSS source
Elevated
10.0EG
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: 0.9%CVSS: 10.0Exploit: No code on recordExposed services: Not assessed

A fix is available — apply it.

Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to a critical Sandbox Escape leading to Remote Code Execution (RCE) in its TableChatAgent and VectorStore capabilities. When these agents evaluate LLM-generated tool messages with full_eval=True, they attempt to sandbox the execution by explicitly setting locals to an empty dictionary {} inside Python's eval() function. However, this relies on an incomplete understanding of Python's execution model. Because __builtins__ is not explicitly scrubbed from the globals dictionary mapping, Python implicitly injects all built-ins during execution, granting full access to functions like __import__('os').system(). Since TableChatAgent.pandas_eval() executes external LLM outputs natively, this bypass permits any attacker providing prompt payload to achieve unauthenticated RCE on the host system. Version 0.65.2 patches the issue.

CVSS v3
10.0
EG Score
10.0CRITICALmedium confidence
EG Risk
76
EG Risk 76/100

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)
Severity100% × 45%
The EG Score, 10.0 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, Track* at medium and Attend at high mission impact.
Exploitation public PoC (CISA Vulnrichment) · Automatable yes (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
0.9%
EPSS %ILE
59th
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 yes (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)3 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 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

July 6, 2026

Last Modified

July 10, 2026

Advisory Details (1)

Auto-updated Oct 17, 2026
🔬 Proof of concept available. Patch available. Sources: github.
GitHub advisoryMentions a patch (unverified)🟡 PoC Available

Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent · Advisory · langroid/langroid · GitHub

https://github.com/langroid/langroid/security/advisories/GHSA-q9p7-wqxg-mrhc

Vendor Advisories for CVE-2026-54769(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)
PyPI(1)
PackageVulnerable rangeFix by version rangeDependents
langroid0.1.100 ... 0.9.5 (534 versions)
  • every version up to 0.65.2: fixed in 0.65.2
—

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 15× in last 7d / 37× 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 146 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 46 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-10-16 18:46 UTCEG score recompute
  2. 2026-10-16 16:42 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  3. 2026-10-15 16:32 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  4. 2026-10-15 15:48 UTCEG score recompute
  5. 2026-10-14 16:33 UTCEPSS rescoreEPSS 0.9% · 59th percentile
  6. 2026-10-14 10:00 UTCEG score recompute
  7. 2026-10-13 16:34 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  8. 2026-10-13 08:08 UTCEG score recompute
  9. 2026-10-12 16:34 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  10. 2026-10-12 15:56 UTCEG score recompute
  11. 2026-10-11 19:39 UTCEG score recompute
  12. 2026-10-11 16:54 UTCEG score recompute
  13. 2026-10-11 14:17 UTCEG score recompute
  14. 2026-10-11 13:49 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  15. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  16. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  17. 2026-10-08 17:12 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  18. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  19. 2026-10-06 15:18 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  20. 2026-10-05 17:43 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  21. 2026-10-04 23:22 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  22. 2026-10-03 14:26 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  23. 2026-10-02 17:56 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  24. 2026-10-01 19:50 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  25. 2026-09-30 15:03 UTCEPSS rescoreEPSS 0.9% · 58th percentile
Show 75 more
  1. 2026-09-29 15:22 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  2. 2026-09-28 13:51 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  3. 2026-09-28 13:41 UTCEG score recompute
  4. 2026-09-27 13:48 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  5. 2026-09-26 15:59 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  6. 2026-09-24 14:04 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  7. 2026-09-23 17:54 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  8. 2026-09-23 06:22 UTCEG score recompute
  9. 2026-09-20 20:16 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  10. 2026-09-18 19:28 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  11. 2026-09-18 05:59 UTCEG score recompute
  12. 2026-09-17 19:31 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  13. 2026-09-16 14:08 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  14. 2026-09-16 05:15 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  15. 2026-09-15 03:11 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  16. 2026-09-13 23:56 UTCEG score recompute
  17. 2026-09-13 16:47 UTCEPSS rescoreEPSS 0.9% · 58th percentile
  18. 2026-09-13 08:43 UTCEG score recompute
  19. 2026-09-12 03:51 UTCEG score recompute
  20. 2026-09-11 14:53 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  21. 2026-09-10 09:35 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  22. 2026-09-08 22:01 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  23. 2026-09-07 16:01 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  24. 2026-09-06 14:10 UTCEG score recompute
  25. 2026-09-06 13:47 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  26. 2026-09-05 23:04 UTCEG score recompute
  27. 2026-09-04 05:06 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  28. 2026-09-02 14:12 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  29. 2026-09-01 13:54 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  30. 2026-09-01 04:40 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  31. 2026-08-30 21:06 UTCEG score recompute
  32. 2026-08-30 19:17 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  33. 2026-08-30 07:59 UTCEG score recompute
  34. 2026-08-30 01:22 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  35. 2026-08-28 21:41 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  36. 2026-08-27 21:58 UTCEG score recompute
  37. 2026-08-27 14:25 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  38. 2026-08-27 02:06 UTCEG score recompute
  39. 2026-08-26 14:46 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  40. 2026-08-25 16:02 UTCEG score recompute
  41. 2026-08-25 13:49 UTCEPSS rescoreEPSS 0.9% · 57th percentile
  42. 2026-08-24 20:44 UTCEG score recompute
  43. 2026-08-24 09:58 UTCEG score recompute
  44. 2026-08-23 01:59 UTCEG score recompute
  45. 2026-08-23 00:19 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  46. 2026-08-22 01:04 UTCEG score recompute
  47. 2026-08-21 23:49 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  48. 2026-08-20 23:49 UTCEG score recompute
  49. 2026-08-20 22:55 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  50. 2026-08-20 02:26 UTCEG score recompute
  51. 2026-08-19 17:04 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  52. 2026-08-18 20:48 UTCEG score recompute
  53. 2026-08-18 13:48 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  54. 2026-08-17 14:08 UTCEG score recompute
  55. 2026-08-17 13:47 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  56. 2026-08-16 18:03 UTCEG score recompute
  57. 2026-08-16 14:56 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  58. 2026-08-16 05:43 UTCEG score recompute
  59. 2026-08-16 02:14 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  60. 2026-08-15 05:33 UTCEG score recompute
  61. 2026-08-15 01:30 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  62. 2026-08-14 01:27 UTCEG score recompute
  63. 2026-08-13 22:00 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  64. 2026-08-12 17:08 UTCEG score recompute
  65. 2026-08-12 13:51 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  66. 2026-08-11 17:00 UTCEG score recompute
  67. 2026-08-11 00:57 UTCEG score recompute
  68. 2026-08-11 00:00 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  69. 2026-08-09 16:20 UTCEG score recompute
  70. 2026-08-09 13:46 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  71. 2026-08-08 20:16 UTCEG score recompute
  72. 2026-08-08 16:37 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  73. 2026-08-07 20:12 UTCEG score recompute
  74. 2026-08-06 16:03 UTCEG score recompute
  75. 2026-08-06 13:47 UTCEPSS rescoreEPSS 0.6% · 47th percentile

Related CVEs(same product + same CWE)

Frequently asked(5)

What is CVE-2026-54769?
CVE-2026-54769 is a critical-severity vulnerability; its CVE record was published on July 6, 2026. Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to a critical Sandbox Escape leading to Remote Code Execution (RCE) in its TableChatAgent and VectorStore capabilities. When these agents evaluate LLM-generated tool messages with…
When was the CVE record for CVE-2026-54769 published?
The CVE record for CVE-2026-54769 was published on July 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 10, 2026; the record at its source may have been updated since.
Is CVE-2026-54769 actively exploited?
CVE-2026-54769 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.9% probability of exploitation in the next 30 days (59th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-54769?
CVE-2026-54769 has a CVSS base score of 10.0 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-54769?
A fix for CVE-2026-54769 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-54769 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-2026-54769

Explore →

Is Your Infrastructure Affected by CVE-2026-54769?

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

Book a Demo →Browse All CVEs