CVE-2026-57143
8.8HighPublished 12 Oct 2026 · NVD status: Received
8.8High
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- None
- User interaction
- Required
- Impact
- High impact on confidentiality
- Weakness
- CWE-20, CWE-918
The AI triage for this one isn't ready yet. Check back in a few minutes; the full NVD record is below in the meantime.
CVSS v3.1 · CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:L/A:L
Ad · In-content banner
NVD 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.
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