Vulnerability  ·  2026-11-19

Obot OAuth access-token theft via unvalidated MCP protected-resource metadata (CVE-2026-130766)

VulnerabilityHigh impactGlobalCVE-2026-130766
Obot trusted the resource identifier in a remote MCP server's OAuth protected-resource metadata without checking it matched the server (RFC 9728 violation). A malicious or compromised remote MCP server could name a different service as the resource, point Obot at an authorization server the victim already uses, and cause Obot to obtain an access token for that other service. Obot then sent the token to the attacker with each request. The authorization server and requested scopes were also attacker-chosen, so the attacker selected which service the token was for and how much access it granted; the victim only saw a legitimate consent screen.
Obot is an agent platform where users connect MCP servers that may be OAuth-protected. This lets a single malicious MCP server harvest a valid access token issued to the victim for an unrelated service (email, storage, SaaS), granting read/write access the victim could consent to — a cross-service OAuth token theft within the agent's own MCP session, bypassing any per-service trust boundary.
Malicious/compromised remote MCP server advertises OAuth protected-resource metadata naming a different service + authorization server + scopes; Obot obtains the victim's access token for that service and forwards it to the attacker on each request.
Obot 0.26.0 through 0.26.3 (fixed in 0.27.0)
Upgrade Obot to 0.27.0 or later, which rejects protected-resource metadata unless the resource origin/path matches the MCP server URL.
Obot security advisory GHSA-x3hf-v55x-jcp6NVD detail — CVE-2026-130766
See this in the live feed Explore related AI security and governance findings — updated every morning.
Open the feed →