Skip to content
Fencer Intel
medium 5.5

CVE-2026-47395 json

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

published 5mo ago modified 3mo ago also EUVD-2026-46303 , GHSA-5cxw-77wg-jrf3 , PYSEC-2026-2903 , PYSEC-2026-2942

cvss
5.5
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.2%
EPSS 0.2% chance of exploitation in 30 days, percentile 7%
public exploits
0
none known

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.

Patch / fix

  • pypi praisonaiagents 1.6.40
  • pypi praisonai 4.6.40
  • praison praisonai 4.6.40
  • praison praisonaiagents 1.6.40

Is CVE-2026-47395 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
partial
Assessed
3mo ago

Exploit prediction

0.18% chance of exploitation in the next 30 days, higher than 7% of all scored CVEs (FIRST EPSS, 2026-11-11).

Exploits and checks

  • github.com https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3 referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 5.5 CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N
GitHub 3.1 5.5 CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N
OSV 3.1 5.5 CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N

Affected packages

ecosystem package affected fixed in
pypi praisonaiagents
<1.6.40
1.6.40
pypi praisonai
<4.6.40
4.6.40

Affected products

  • MervinPraison PraisonAI
  • MervinPraison praisonaiagents

Classification

Weakness
  • CWE-200 Exposure of Sensitive Information to an Unauthorized Actor

References

Sources

Fencer Intel 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.