Read the docs
TI-2026-79611 Aliases CVE-2026-56834

PraisonAI artifact tools read host files outside artifact storage

Priority HIGH 72CWE-200Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
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, a multi-agent teams system, is affected from version 3.8.1 before 4.6.59. Its Dynamic Context Discovery feature exposes artifact helper tools through ctx.get_tools() that do not check whether the supplied artifact_path belongs to the configured store or lies under its base directory, which is a path traversal flaw (CWE-22). An attacker who can influence the arguments of these tools, for example through a prompt, can read any file the PraisonAI process can read, such as .env files, cloud credentials or SSH keys. The flaw is exposed through the artifact_head, artifact_tail, artifact_grep and artifact_chunk tools.

Written with Claude Haiku 5.5 from the sources below · 2026-10-29

Description from the CNA

PraisonAI is a multi-agent teams system. From version 3.8.1 to before version 4.6.59, PraisonAI's Dynamic Context Discovery feature exposes artifact helper tools through ctx.get_tools(). The implemented artifact tools do not enforce that the supplied artifact_path is an artifact created by the configured store or that it lives under the configured artifact base directory. Instead, artifact_head, artifact_tail, artifact_grep, and artifact_chunk wrap the caller-supplied path directly into an ArtifactRef and then read it from the host filesystem. As a result, any prompt/user/tool-caller that can influence those tool arguments can read files readable by the PraisonAI process, such as project .env files, cloud credentials, SSH keys, source files, or other local data. This issue has been patched in version 4.6.59.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.00373 31st percentileScored 2026-11-07
Fix Fixed PraisonAI (MervinPraison): 4.6.59praisonai (PyPI): 4.6.59

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
Poc
Automatable
Yes
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
MervinPraisonPraisonAI3.8.1 to before 4.6.594.6.59Patch availableCNA
—praisonai (PyPI)3.8.1 to before 4.6.594.6.59Patch availableGHSA-j7qx-p75m-wp7g
  • PraisonAI VendorMervinPraison Affected 3.8.1 to before 4.6.59 Fixed in 4.6.59 Patch available CNA
  • praisonai (PyPI) Vendor— Affected 3.8.1 to before 4.6.59 Fixed in 4.6.59 Patch available GHSA-j7qx-p75m-wp7g

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

Upgrade the PyPI package praisonai to version 4.6.59, which fixes the issue. The sources list no fixed version for PraisonAI from MervinPraison.

Written with Claude Haiku 5.5 from the sources below · 2026-10-29

  • Fix · CNA PraisonAI (MervinPraison) Fixed in 4.6.59
  • Fix · GHSA-j7qx-p75m-wp7g praisonai (PyPI) Fixed in 4.6.59 Advisory →

Timeline

  1. 2026-10-23 Threatist record created from CVE-2026-56834
  2. 2026-10-24 Priority changed: MEDIUM → LOW
  3. 2026-10-29 CISA SSVC decision points changed
  4. 2026-10-29 Priority changed: LOW → HIGH

References

Other 2

  • 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

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences