CVE-2026-57143Public exploitNetwork attack vectorHinoki check available

Internal-service disclosure via unvalidated search URLs

Published Oct 12, 2026 · Updated Oct 12, 2026

SSRF in PraisonAI praisonaiagents before 1.6.62 allows remote attackers to read internal JSON services via prompt injection. The searxng_search and search_web SearxNG paths pass LLM-controlled searxng_url directly to requests.get without destination validation, returning parsed JSON results into agent context. Exploitation requires ingestion of attacker-controlled content with the search tool enabled; internal ports can be probed, but raw cloud-metadata responses are not returned without a results key.

CVSS severity8.8
High
EPSS probability0.22%
Next 30 days · Oct 19, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkAvailable
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Get started

Summary

What happened

SSRF in PraisonAI praisonaiagents before 1.6.62 allows remote attackers to read internal JSON services via prompt injection. The searxng_search and search_web SearxNG paths pass LLM-controlled searxng_url directly to requests.get without destination validation, returning parsed JSON results into agent context. Exploitation requires ingestion of attacker-controlled content with the search tool enabled; internal ports can be probed, but raw cloud-metadata responses are not returned without a results key.

The record

CVE
CVE-2026-57143
Published
Oct 12, 2026
Updated
Oct 12, 2026
Vendor
PraisonAI
Product
praisonaiagents
Classifications
CWE-918, CWE-20, T1046
Attack vector
network
Privileges
unauthenticated

Timeline

How it unfolded

  1. Oct 12, 2026CVE publishedPublication date reported by the CVE source.
  2. Oct 12, 2026Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=< 1.6.62

What conditions does exploitation require?

Attack vectornetwork
Required privilegesunauthenticated

What is affected?

PraisonAI · praisonaiagentsversion=< 1.6.62

Published CVSS scores

8.8GitHub CNACVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:L/A:L

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Activity data is delayed. The latest report is Sep 28, 2026.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 22, 2026Sep 28, 2026
Latest reporting daySep 28, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesunauthenticated
Known exploitationUnconfirmed
Public exploitPublished

Weakness, pattern, technique

CWE-918Server-Side Request Forgery (SSRF)
CWE-20Improper Input Validation
T1046Network Service Discovery

Public exploit references

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Get started to see how Hinoki identifies affected software and validates exploitability in your environment.

Get started