Skip to content
Fencer Vulns
high 7.5

CVE-2026-56834 json

PraisonAI dynamic-context artifact tools read arbitrary host files outside artifact storage

published 2026-06-18 4 mo ago modified 2026-10-29 11 d ago also EUVD-2026-108875 , GHSA-j7qx-p75m-wp7g , PYSEC-2026-3514

cvss
7.5
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.4%
EPSS 0.4% chance of exploitation in 30 days, percentile 31%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi praisonai 4.6.59
  • praison praisonai 4.6.59

CISA SSVC

Exploitation
Proof of concept is public
Automatable
yes
Technical impact
partial
Assessed
11 d ago

Exploit prediction

0.37% chance of exploitation in the next 30 days, higher than 31% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

  • github.com https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-j7qx-p75m-wp7g referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
GitHub 3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
OSV 3.1 7.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Affected packages

ecosystem package affected fixed in
pypi praisonai
>=3.8.1, <4.6.59
4.6.59

Affected products

  • MervinPraison PraisonAI

Classification

Weakness
  • CWE-22 Improper Limitation of a Pathname to a Restricted Directory
  • CWE-200 Exposure of Sensitive Information to an Unauthorized Actor

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.