Read the docs
TI-2026-34965 Aliases CVE-2026-47395GHSA-5cxw-77wg-jrf3

PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context

Priority MEDIUM 58CWE-200Published · Updated

Key facts

Attack vector
Local
Privileges required
None
User interaction
Required
Attack complexity
Low
Impact type
Information disclosure
Confidentiality · integrity · availability
High · None · None
Fix status
Fixed

Attack profile from CVSS 3.1 · CNA. Fix status from CNA and GitHub. Impact type from CWE-200.

Summary

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands `@url:` mentions in raw prompt text before agent execution begins. If a prompt contains `@url:<http-or-https-url>`, the CLI calls `MentionsParser.process(...)`. The `@url:` handler then performs a direct `urllib.request.urlopen()` request to the attacker-controlled URL and returns the response body. That response body is prepended to the final model prompt context. There is no loopback/private-address restriction, no metadata-service restriction, and no approval gate before the fetch. As a result, attacker-influenced prompt text can cause the operator's machine to fetch localhost-only HTTP resources and inject the response into model context. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a fix.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.00183 7th percentileScored 2026-11-07
Fix Fixed PraisonAI (MervinPraison): 4.6.40praisonaiagents (MervinPraison): 1.6.40+2 more products

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
Poc
Automatable
No
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
MervinPraisonPraisonAIbefore 4.6.404.6.40Patch availableCNA
MervinPraisonpraisonaiagentsbefore 1.6.401.6.40Patch availableCNA
—praisonaiagents (PyPI)before 1.6.401.6.40Patch availableGHSA-5cxw-77wg-jrf3
—PraisonAI (PyPI)before 4.6.404.6.40Patch availableGHSA-5cxw-77wg-jrf3
  • PraisonAI VendorMervinPraison Affected before 4.6.40 Fixed in 4.6.40 Patch available CNA
  • praisonaiagents VendorMervinPraison Affected before 1.6.40 Fixed in 1.6.40 Patch available CNA
  • praisonaiagents (PyPI) Vendor— Affected before 1.6.40 Fixed in 1.6.40 Patch available GHSA-5cxw-77wg-jrf3
  • PraisonAI (PyPI) Vendor— Affected before 4.6.40 Fixed in 4.6.40 Patch available GHSA-5cxw-77wg-jrf3

CPE names Threatist (inferred) · 1

Inferred from how NVD named this product before; not given by a source.

CPEVersionsRoleVendor
cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:*——MervinPraison
  • cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:* Versions — — ·MervinPraison

Remediation

  • Fix · CNA PraisonAI (MervinPraison) Fixed in 4.6.40
  • Fix · CNA praisonaiagents (MervinPraison) Fixed in 1.6.40
  • Fix · GHSA-5cxw-77wg-jrf3 praisonaiagents (PyPI) Fixed in 1.6.40 Advisory →
  • Fix · GHSA-5cxw-77wg-jrf3 PraisonAI (PyPI) Fixed in 4.6.40 Advisory →

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-47395
  2. 2026-10-03 Alias added: GHSA-5cxw-77wg-jrf3

References

  • TI-2026-79619 Missing authentication in PraisonAI AgentOS exposes agent chat CVSS 3.1CRITICAL 9.8
  • TI-2026-71236 Missing access control in PraisonAI AgentTeam exposes agent endpoints CVSS 3.1CRITICAL 9.8
  • TI-2026-44052 PraisonAI before 1.6.78 Remote Code Execution via CodeAgent CVSS 4.0CRITICAL 10.0
  • TI-2026-41123 praisonai-platform 0.1.4 still boots on the hardcoded JWT secret dev-secret-change-me (default-open production guard) CVSS 3.1CRITICAL 9.8
  • TI-2026-41122 praisonai-platform: default JWT signing secret 'dev-secret-change-me' enables token forgery CVSS 3.1CRITICAL 9.8
  • TI-2026-41118 PraisonAI MCPServer exposes unauthenticated HTTP tools/call CVSS 3.1CRITICAL 9.8
See all 177 →

Sources