PraisonAIAgents before version 1.5.128 contains an SSRF vulnerability (CWE-918) in its web_crawl module. The httpx fallback path uses user-supplied URLs directly in asynchronous HTTP GET requests with automatic redirect following and no validation of the host. This enables an attacker controlling an LLM agent to induce requests to internal IP addresses and services, including cloud metadata endpoints, potentially exposing sensitive internal data. The vulnerability is resolved in version 1.5.128.

An attacker can exploit this SSRF vulnerability to make the PraisonAIAgents system send HTTP requests to internal network resources, including cloud metadata services and localhost. The responses from these internal services are returned to the agent and may be visible to the attacker, potentially leading to information disclosure of sensitive internal data. There is no indication of remote code execution or privilege escalation from the provided data.

Upgrade PraisonAIAgents to version 1.5.128 or later, where this SSRF vulnerability is fixed. Since no official patch link or advisory is provided, users should verify the update availability from the vendor or official distribution channels. Patch status is not explicitly confirmed beyond the version fix note; therefore, check the vendor advisory for current remediation guidance.