nday
CVE-2026-47395 GHSA-5cxw-77wg-jrf3

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

MervinPraison / PraisonAI, praisonaiagents

Disclosed . nday has no fix record for it yet; that does not mean no patch exists. None of the four PoC sources lists it. Not in CISA KEV.

why these tags

nday derives these tags by fixed rules from the facts below; NVD, the CNA and other sources do not assign them. Vocabulary and rules: ~/tags.

information disclosure
CWE-200, stated by the CNA GitHub_M and NVD, republishing [email protected]
local
AV:L in CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N (CVSS 3.1) from the CNA GitHub_M
no authentication required
PR:N in CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N (CVSS 3.1) from the CNA GitHub_M
stage
DIS
disclosed
cvss
5.5 MEDIUM v3.1

Lifecycle

x axis UTC; dot = exact minute, wide bar = date only, hollow = unknown or inferred.
time unknown
DISdisclosed
07-21T15:52Z
PATpatch
no record yet
ANAanalysis
no record yet
POCPoC
no record yet
ITWexploited
no record yet
KEVKEV
no record yet

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.

Original text of the CVE record (cvelist), shown as published.

Exploit conditions

What an attack needs, read from the CVSS vector.
Attack vector AV:L
Local: needs a local or SSH session, or a user tricked into acting on the machine
Attack complexity AC:L
Low: no special conditions; the attacker can expect repeatable success
Privileges required PR:N
None: no account or authorization needed
User interaction UI:R
Required: a user must do something, such as open a file or click a link

CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N

CVSS 3.1 vector from the CVE record, scored by the CNA GitHub_M.

Event log

+DISdisclosed

CVE record published by GitHub_M. CVSS 5.5, medium. CISA's SSVC assessment rates exploitation as poc.

src cvelist · nday , bulk import · raw
{
  "id": 427226,
  "type": "disclosed",
  "source": "cvelist",
  "url": "https://www.cve.org/CVERecord?id=CVE-2026-47395",
  "occurred_at": "2026-07-21T15:52:52.682Z",
  "observed_at": "2026-11-13T05:39:52.052485Z",
  "is_backfill": true,
  "dedupe_key": "",
  "detail": {
    "cvss": {
      "source": "cna",
      "vector": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N",
      "version": "3.1",
      "base_score": 5.5,
      "base_severity": "MEDIUM"
    },
    "ssvc": {
      "timestamp": "2026-07-21T17:09:32.354388Z",
      "automatable": "no",
      "exploitation": "poc",
      "technical_impact": "partial"
    },
    "state": "PUBLISHED",
    "date_published": "2026-07-21T15:52:52.682Z",
    "assigner_short_name": "GitHub_M"
  }
}

Report an error

report an error or omission

Something on this page wrong or missing? Tell the editors; if they accept it, this page's revision log says so publicly. Upstream data is not changed.

Researcher discussion

0 researchers mentioned this in the last 7 days

Posts on X by researchers on nday's list that mention this CVE, shown as posted. nday does not check them.

nday has not collected any post on X by listed researchers that mentions this CVE.

Discussion

0 comments

No comments yet.