Impact
The vulnerability resides in the LLM Models API llm.js of JoeCastrom mcp-chat-studio. Manipulating the req.query.base_url parameter triggers a server‑side request forgery, allowing a remote attacker to instruct the server to send arbitrary HTTP requests to internal or external resources. The capability to perform these requests is inferred from the nature of SSRF, but the specific consequences such as file disclosure or command execution are not detailed in the description. The weakness corresponds to CWE‑918.
Affected Systems
JoeCastrom mcp-chat-studio up to version 1.5.0 is impacted. The known affected component is the server/routes/llm.js file within the LLM Models API. Users running any releases preceding or equal to 1.5.0 should verify their deployment. No patch or version guarantee is listed in the input.
Risk and Exploitability
The CVSS base score is 6.9, signalling a moderate to high severity. The EPSS score is < 1%, indicating a very low exploitation probability, and the vulnerability is not listed in CISA’s KEV, but the public exploit indicates that adversaries could target affected installations. The attack vector is inferred from the description; it requires a crafted base_url value to trigger SSRF. The absence of an official fix means the risk remains until mitigation is applied.
OpenCVE Enrichment