← All CVEs

CVE-2026-47395

MEDIUM 5.5 PoC AVAILABLE

Published 2026-07-21 · Last modified 2026-07-21

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.

EXPLOIT AVAILABLE

Public exploit or PoC code exists. Modeled probability is still low, but the barrier to attack is reduced — watch closely.

Exploitation likelihood

EPSS not yet scored

○ In CISA KEV ● Public exploit / PoC

Impact if exploited

5.5CVSS 3.1 · MEDIUM

  • ConfidentialityHigh
  • IntegrityNone
  • AvailabilityNone

What an attacker needs

  • Access: Requires local access to the host
  • Privileges: No account or privileges required
  • User interaction: A user must take an action (click / open a file)
  • Complexity: No special conditions — reliably repeatable

✓ lowers the bar for an attacker · ⚠ raises it

Proof of concept & exploit code

Test against your own equipment

curl -s https://vulnpedia.com/cve/CVE-2026-47395/poc.jsonMachine-readable PoC index for this CVE (for automation).

Listed for defensive triage, patch verification, and authorized testing on systems you own. Machine-readable: /cve/CVE-2026-47395/poc.json

Affected

Vendors Mervinpraison

Products Praisonai Praisonaiagents

Weakness (CWE)

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

CVSS vector

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

All CVSS metrics

  • MEDIUM 5.5 v3.1 · CNA Primary
    CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N
  • MEDIUM 5.5 v3.1 · NVD Secondary
    CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N

Sources: NVD · CVE.org · EPSS