Server-side request forgery in PraisonAI SearxNG search tools
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- Required
- Attack complexity
- Low
- Impact type
- —
- Confidentiality · integrity · availability
- High · Low · Low
- Fix status
- Fixed
Attack profile from CVSS 3.1 · CNA. Fix status from CNA and GitHub.
Summary
PraisonAI praisonaiagents before 1.6.62 passes the searxng_url parameter to an outbound HTTP request without validating its scheme, host, port, or address. The flaw is a server-side request forgery (CWE-918) in the searxng_search and search_web SearxNG providers. An attacker who injects prompts into content the agent reads can direct the default search tool to internal services and cloud metadata endpoints, and the JSON results enter the agent context. User interaction is required.
Written with Claude Haiku 5.5 from the sources below · 2026-10-29
Description from the CNA
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.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- Poc
- Automatable
- No
- Technical impact
- Partial
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| MervinPraison | praisonaiagents | before 1.6.62 | 1.6.62 | Patch available | CNA |
| — | praisonaiagents (PyPI) | before 1.6.61 | 1.6.61 | Patch available | GHSA-4pcv-mg8v-vrgf |
- praisonaiagents VendorMervinPraison Affected before 1.6.62 Fixed in 1.6.62 Patch available CNA
- praisonaiagents (PyPI) Vendor— Affected before 1.6.61 Fixed in 1.6.61 Patch available GHSA-4pcv-mg8v-vrgf
Remediation
Upgrade praisonaiagents to 1.6.62, the fixed version named in the advisory. The PyPI entry instead lists 1.6.61 as fixed, so the sources disagree.
Written with Claude Haiku 5.5 from the sources below · 2026-10-29
- Fix · CNA praisonaiagents (MervinPraison) Fixed in 1.6.62
- Fix · GHSA-4pcv-mg8v-vrgf praisonaiagents (PyPI) Fixed in 1.6.61 Advisory →
Timeline
- 2026-10-12 Threatist record created from CVE-2026-57143
- 2026-10-13 CISA SSVC decision points changed
- 2026-10-13 Priority changed: MEDIUM → HIGH
References
More MervinPraison vulnerabilities
- TI-2026-79619 Missing authentication in PraisonAI AgentOS exposes agent chat CVSS 3.1CRITICAL 9.8
- TI-2026-71236 Missing access control in PraisonAI AgentTeam exposes agent endpoints CVSS 3.1CRITICAL 9.8
- TI-2026-44052 PraisonAI before 1.6.78 Remote Code Execution via CodeAgent CVSS 4.0CRITICAL 10.0
- TI-2026-41123 praisonai-platform 0.1.4 still boots on the hardcoded JWT secret dev-secret-change-me (default-open production guard) CVSS 3.1CRITICAL 9.8
- TI-2026-41122 praisonai-platform: default JWT signing secret 'dev-secret-change-me' enables token forgery CVSS 3.1CRITICAL 9.8
- TI-2026-41118 PraisonAI MCPServer exposes unauthenticated HTTP tools/call CVSS 3.1CRITICAL 9.8
Sources
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences