CVE-2026-55533

HIGHPre-NVD 8.28.2
EchelonGraph scoreMEDIUM confidence

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

This high-severity CVE scores 8.2 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.5% (40th 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
8.2EG
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: 8.2Exploit: No code on recordExposed services: Not assessed

A fix is available — apply it.

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, create_auth_middleware() allows requests when auth=api-key lacks PRAISONAI_API_KEY or JWT authentication lacks PRAISONAI_JWT_SECRET. An externally bound Recipe server can therefore accept unauthenticated POST /v1/recipes/run requests despite authentication being enabled. This issue is fixed in version 4.6.58.

CVSS v3
8.2
EG Score
8.2HIGHmedium confidence
EG Risk
68
EG Risk 68/100

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)
Severity82% × 45%
The EG Score, 8.2 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: 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
40th
KEV
Not listed

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

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 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

August 25, 2026

Last Modified

September 9, 2026

Advisory Details (3)

Auto-updated Aug 25, 2026
Patch available. Sources: github_release, github, github_commit.
GitHub release Patch Available

PraisonAI v4.6.58

Patch available: MervinPraison/PraisonAI v4.6.58

https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.58
GitHub commit Patch Available

commit 2f9677abb2ea (MervinPraison/PraisonAI)

Patch available: MervinPraison/PraisonAI v4.6.137 (contains commit 2f9677abb2ea)

https://github.com/MervinPraison/PraisonAI/commit/2f9677abb2ea68eab864ee8b6a828fd0141612e1
GitHub advisoryMentions a patch (unverified)

Authentication fail-open in Recipe server allows unauthenticated access when API key or JWT auth is configured without a secret · Advisory · MervinPraison/PraisonAI · GitHub

https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gfq8-hmph-9gjv

Vendor Advisories for CVE-2026-55533(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
praisonai0.0.1 ... 4.6.9 (748 versions)
  • every version up to 4.6.58: fixed in 4.6.58
—

Weakness Classification(2)

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

Data Freshness Timeline

(refreshed 14× in last 7d / 55× 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.

  1. 2026-10-13 16:34 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  2. 2026-10-12 16:34 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  3. 2026-10-12 15:41 UTCEG score recompute
  4. 2026-10-11 19:39 UTCEG score recompute
  5. 2026-10-11 16:54 UTCEG score recompute
  6. 2026-10-11 14:17 UTCEG score recompute
  7. 2026-10-11 13:49 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  8. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  9. 2026-10-10 12:03 UTCEG score recompute
  10. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  11. 2026-10-09 04:23 UTCEG score recompute
  12. 2026-10-08 17:12 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  13. 2026-10-08 03:17 UTCEG score recompute
  14. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  15. 2026-10-06 19:49 UTCEG score recompute
  16. 2026-10-06 15:18 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  17. 2026-10-06 07:43 UTCEG score recompute
  18. 2026-10-05 17:43 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  19. 2026-10-05 04:48 UTCEG score recompute
  20. 2026-10-04 23:22 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  21. 2026-10-03 16:26 UTCEG score recompute
  22. 2026-10-03 14:26 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  23. 2026-10-02 21:33 UTCEG score recompute
  24. 2026-10-02 17:56 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  25. 2026-10-01 20:58 UTCEG score recompute
Show 67 more
  1. 2026-10-01 19:50 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  2. 2026-09-30 20:15 UTCEG score recompute
  3. 2026-09-30 15:03 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  4. 2026-09-30 06:48 UTCEG score recompute
  5. 2026-09-29 15:22 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  6. 2026-09-28 22:35 UTCEG score recompute
  7. 2026-09-28 13:51 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  8. 2026-09-27 22:21 UTCEG score recompute
  9. 2026-09-27 13:48 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  10. 2026-09-26 22:05 UTCEG score recompute
  11. 2026-09-26 15:59 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  12. 2026-09-25 01:55 UTCEG score recompute
  13. 2026-09-24 14:04 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  14. 2026-09-24 01:40 UTCEG score recompute
  15. 2026-09-23 17:54 UTCEPSS rescoreEPSS 0.3% · 27th percentile
  16. 2026-09-23 01:25 UTCEG score recompute
  17. 2026-09-22 01:11 UTCEG score recompute
  18. 2026-09-21 00:56 UTCEG score recompute
  19. 2026-09-20 20:16 UTCEPSS rescoreEPSS 0.3% · 27th percentile
  20. 2026-09-20 00:41 UTCEG score recompute
  21. 2026-09-19 00:25 UTCEG score recompute
  22. 2026-09-18 19:28 UTCEPSS rescoreEPSS 0.3% · 27th percentile
  23. 2026-09-18 00:05 UTCEG score recompute
  24. 2026-09-17 19:31 UTCEPSS rescoreEPSS 0.3% · 27th percentile
  25. 2026-09-16 23:49 UTCEG score recompute
  26. 2026-09-16 14:08 UTCEPSS rescoreEPSS 0.3% · 27th percentile
  27. 2026-09-16 11:42 UTCEG score recompute
  28. 2026-09-16 05:15 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  29. 2026-09-15 11:12 UTCEG score recompute
  30. 2026-09-15 03:11 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  31. 2026-09-13 22:21 UTCEG score recompute
  32. 2026-09-13 16:47 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  33. 2026-09-12 22:06 UTCEG score recompute
  34. 2026-09-11 21:51 UTCEG score recompute
  35. 2026-09-11 14:53 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  36. 2026-09-11 09:44 UTCEG score recompute
  37. 2026-09-10 21:35 UTCEG score recompute
  38. 2026-09-10 09:35 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  39. 2026-09-09 01:14 UTCEG score recompute
  40. 2026-09-08 22:01 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  41. 2026-09-07 22:14 UTCEG score recompute
  42. 2026-09-07 16:01 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  43. 2026-09-06 21:55 UTCEG score recompute
  44. 2026-09-06 13:47 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  45. 2026-09-05 21:32 UTCEG score recompute
  46. 2026-09-04 21:17 UTCEG score recompute
  47. 2026-09-04 09:10 UTCEG score recompute
  48. 2026-09-04 05:06 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  49. 2026-09-02 20:44 UTCEG score recompute
  50. 2026-09-02 14:12 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  51. 2026-09-01 19:55 UTCEG score recompute
  52. 2026-09-01 13:54 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  53. 2026-09-01 07:48 UTCEG score recompute
  54. 2026-09-01 04:40 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  55. 2026-08-31 07:16 UTCEG score recompute
  56. 2026-08-30 19:17 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  57. 2026-08-30 06:59 UTCEG score recompute
  58. 2026-08-30 01:22 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  59. 2026-08-29 06:44 UTCEG score recompute
  60. 2026-08-28 21:41 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  61. 2026-08-27 18:11 UTCEG score recompute
  62. 2026-08-27 14:25 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  63. 2026-08-26 17:46 UTCEG score recompute
  64. 2026-08-26 14:46 UTCEPSS rescoreEPSS 0.3% · 26th percentile
  65. 2026-08-25 16:24 UTCEG score recompute
  66. 2026-08-25 15:30 UTCEG score recomputeFirst assessed: 8.2 HIGH
  67. 2026-08-25 15:29 UTCMITRE cvelistV5first tracked

Related CVEs(same product + same CWE)

Frequently asked(5)

What is CVE-2026-55533?
CVE-2026-55533 is a high-severity vulnerability; its CVE record was published on August 25, 2026. PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, createauthmiddleware() allows requests when auth=api-key lacks PRAISONAIAPIKEY or JWT authentication lacks PRAISONAIJWTSECRET. An externally bound Recipe server can therefore accept unauthenticated POST /v1/recipes/run requests…
When was the CVE record for CVE-2026-55533 published?
The CVE record for CVE-2026-55533 was published on August 25, 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 September 9, 2026; the record at its source may have been updated since.
Is CVE-2026-55533 actively exploited?
CVE-2026-55533 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.5% probability of exploitation in the next 30 days (40th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-55533?
CVE-2026-55533 has a CVSS base score of 8.2 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-55533?
A fix for CVE-2026-55533 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-55533 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-2026-55533

Explore →

Is Your Infrastructure Affected by CVE-2026-55533?

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

Book a Demo →Browse All CVEs