CVE-2026-57143
Prompt-injected content can direct the default search tool to internal JSON services, distinguish open and closed internal ports, and attempt cloud-metadata requests, with returned JSON results entering agent context.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.27%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
Description
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.62, searxng_search and the search_web SearxNG provider pass the LLM-controlled searxng_url parameter directly to requests.get without validating its scheme, host, port, or resolved address. Prompt-injected content can direct the default search tool to internal JSON services, distinguish open and closed internal ports, and attempt cloud-metadata requests, with returned JSON results entering agent context. This issue is fixed in praisonaiagents 1.6.62.
- CVSS 3.1
- 8.8 HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:L/A:L
- EPSS
- 0.27% probability · 20th percentile
- Public exploits
- None in Exploit-DB
- CISA KEV
- Not listed
- Weakness
- CWE-20, CWE-918
- Source
- security-advisories@github.com
EPSS moved from 0.2% on 13 October 2026 to 0.3% on 26 October 2026.
References
- https://github.com/MervinPraison/PraisonAI/commit/2a855c470077c7d2e2479a575f7ef7f548d51c33
- https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4pcv-mg8v-vrgf
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4pcv-mg8v-vrgf
Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.