Skip to main content

mcp-fetch EUVDEUVD-2026-66386

| CVE-2026-80347 HIGH
Server-Side Request Forgery (SSRF) (CWE-918)
2026-08-26 VulnCheck
8.7
CVSS 4.0 · Vendor: VulnCheck
Share

Severity by source

Vendor (VulnCheck) PRIMARY
8.7 HIGH
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
vuln.today AI
8.6 HIGH

Network-reachable via prompt injection, no credentials required, scope changes to internal hosts; confidentiality-only impact with no integrity or availability consequence described.

3.1 AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N
4.0 AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:H/SI:N/SA:N

Primary rating from Vendor (VulnCheck).

CVSS VectorVendor: VulnCheck

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
X

Lifecycle Timeline

2
Analysis Generated
Aug 26, 2026 - 10:47 vuln.today
CVE Published
Aug 26, 2026 - 10:09 cve.org
HIGH 8.7

DescriptionCVE.org

mcp-fetch checks a fetch target against its SSRF guard without removing the brackets that surround an IPv6 literal. isSafeUrl reads the hostname from the parsed URL, which for a literal such as http://[::1]/ yields the bracketed string, and then tests it with net.isIP. That call returns zero for a bracketed value, so the branch holding the private-address checks is skipped entirely. The guard falls back to resolving the hostname, the bracketed string is not a resolvable name, no addresses are returned, and the target is reported safe. The HTTP client then strips the brackets and connects. Because the address may be given in IPv4-mapped form, the same path reaches any IPv4 target the loopback and private checks were meant to exclude, including link-local metadata endpoints. isPrivateIPv6 also has no case for the ::ffff: prefix, so the mapped form would still pass even if the brackets were removed. The fetch target is supplied as a tool argument, so an attacker who can influence what the model requests can read internal responses back into the model context.

AnalysisAI

Server-Side Request Forgery in mcp-fetch through version 1.6.3 allows unauthenticated attackers who can influence model tool arguments to bypass the SSRF guard entirely and reach loopback, private, and link-local network endpoints including cloud instance metadata services. The bypass exploits a parsing gap: the guard tests the bracketed IPv6 literal string such as [::1] against Node.js's net.isIP(), which returns zero for bracketed input, causing the private-address branch to be skipped; the HTTP client later strips the brackets and connects normally. …

Unlock full vulnerability intelligence

  • Risk assessment & exploitation conditions
  • Attack chain visualization
  • Remediation with exact patch versions
  • Threat intelligence from 22 sources
  • Personal watchlist & email alerts

Free forever · No credit card required

Attack ChainAIDerived

Hypothetical attack flow derived from CVE metadata

Access
Inject prompt via untrusted content
Delivery
Supply IPv6-bracketed or mapped-form private URL
Exploit
SSRF guard skips private-IP checks
Execution
HTTP client strips brackets, connects to internal host
Persist
Internal service response captured
Impact
Sensitive data returned to model context

Vulnerability AssessmentAI

Exploitation Exploitation requires the ability to influence the URL argument passed to the mcp-fetch tool, which in practice means injecting content - typically via prompt injection in externally fetched text, user-supplied prompts, or adversarial documents - that directs the model to invoke the fetch tool with a crafted URL. … Additional conditions and limiting factors are described in the full assessment.
Risk Assessment The CVSS 4.0 vector AV:N/AC:L/AT:N/PR:N/UI:N/VC:H scoring 8.7 reflects the reality that no prerequisites are required beyond the ability to inject a URL argument into the model's tool call - consistent with typical prompt-injection workflows against AI agents. … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in.
Exploit Scenario An attacker embeds a prompt-injection instruction inside a web page or document that an AI agent using mcp-fetch is directed to fetch. The injected instruction directs the model to call the fetch tool with the URL http://[::ffff:169.254.169.254]/latest/meta-data/iam/security-credentials/ - a cloud metadata endpoint expressed in IPv4-mapped IPv6 form with brackets. …
Remediation No vendor-released patched version is identified in the available data; monitor the upstream repository at https://github.com/kazuph/mcp-fetch and the open issue at https://github.com/kazuph/mcp-fetch/issues/16 for a fix release. … Detailed patch versions, workarounds, and compensating controls in full report.

Recommended ActionAI

Within 24 hours: Identify all systems running mcp-fetch version 1.6.3 or earlier and assess their network exposure (user-facing LLM applications, API endpoints, systems processing untrusted inputs); immediately restrict network access for exposed instances to block external connectivity. …

Sign in for detailed remediation steps and compensating controls.

Threat intelligence, references, and detailed analysis are available after sign-in.

Share

EUVD-2026-66386 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy