Browse / Tool and Agent Misuse / Server-side request forgery
Server-side request forgery
4 records in Tool and Agent Misuse.
- praisonaiagents web_crawl vulnerable to SSRF via redirect-following The agent's web crawl tool checks only the initial URL, then follows attacker-supplied redirects to internal addresses and returns their contents to the model.
- AgentScope vulnerable to Server-Side Request Forgery Image and audio URL arguments passed to AgentScope's multimodal tools are fetched server-side without checks, so a model-supplied URL can reach cloud metadata endpoints.
- PraisonAIAgents has SSRF and Local File Read via Unvalidated URLs in web_crawl Tool The web_crawl agent tool fetches any supplied URL without validation, so injected content can make the agent reach internal hosts or local files.
- Markdownify MCP Server allows Server-Side Request Forgery (SSRF) via the Markdownify.get() function Attacker-authored prompt content makes the MCP host call the server's conversion tools, which fetch attacker-chosen URLs and return the responses.