Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐹 Go

GHSA-vw82-7fv8-r6gp

CRITICAL

Obot has an authorization bypass in /mcp-connect/{id} that allows any authenticated user to use any registered MCP server

Also known asGO-2026-5678
Published
May 13, 2026
Updated
Jun 25, 2026
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed

Blast Radius

1 pkg affected
🐹github.com/obot-platform/obot

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects Go packages — download data is not available via public APIs for these ecosystems.

Description

Summary

If you have the MCP Server ID, you can connect to the MCP server even if you don't have permissions to the server.

The MCP gateway endpoint /mcp-connect/{mcp_id} does not enforce Access Control Rules (ACRs). Any authenticated Obot user who possesses an MCP Server ID can connect to that server through the gateway — including making tool calls — regardless of whether they are a member of any MCP Registry that grants access to the server.

In practice this means any User can fully use MCP servers that the administrator believed were restricted to specific groups.

Severity

Reporter estimate: Critical.

CVSS 3.1 metricValue
Attack VectorNetwork
Attack ComplexityLow
Privileges RequiredLow (authenticated Obot user, any role ≥ Basic)
User InteractionNone
ScopeChanged (Obot authorization bypass enables access to data and operations on an upstream third-party service via Obot's stored OAuth credentials)
ConfidentialityHigh
IntegrityHigh (many MCP servers expose write tools — e.g. updateEmployee, submitTimeoffRequest, ticket creation, file writes)
AvailabilityNone
VectorCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N
Score9.3 / Critical

The upstream impact depends on which MCP servers are deployed and what scope their stored credentials hold; the bound is "everything the platform's stored OAuth/API credentials can reach."

Affected Versions

Confirmed on obot v0.21.0.

Vulnerability Details

The intended flow is that a user's authorization is checked during the OAuth process with Obot.

  1. The user connects to an MCP URL through Obot.
  2. During the callback, after the user logs into Obot, Obot checks that the user has access to the provided resource (the /mcp-connect URL in this case). Obot correctly determines the user's authorization during this flow.
  3. However, another authorization check (the UI authorizer, in this case) was erroneously providing access.

Reproduction

Tested on obot v0.21.0.

Setup:

  1. Configure a multi-user MCP server connected to a sensitive backend — e.g. an HR system, ticketing system, or any service whose stored OAuth token grants broad read/write access. Note its ID.
  2. Create an MCP Registry / Access Control Rule that grants this server only to a small group (e.g. two HR employees). Remove the everyone group from the relevant rule.
  3. Create or identify a Basic User who is not a member of any registry granting access to this server.

Exploit:

  1. Sign in as the Basic User.

  2. Verify the UI does not list the server in any connector picker (it does not — that path is correctly gated).

  3. Manually craft and call the gateway URL:

    POST https://<obot>/mcp-connect/<mcp_server_id>
    Authorization: <session cookie or API key>
    Content-Type: application/json
    
    {"jsonrpc":"2.0","id":1,"method":"tools/list"}
    
  4. Observe a successful response listing the server's tools.

  5. Issue an actual tool call:

{"jsonrpc":"2.0","id":2,"method":"tools/call",
 "params":{"name":"<sensitive_tool>","arguments":{...}}}
  1. Observe the call succeeds, returning data scoped only by the upstream MCP server's OAuth credentials — not by Obot's ACRs.

The exploit works equally well via Claude Desktop / Claude Code / any MCP-aware client by configuring the gateway URL as a remote MCP endpoint with the user's API key.

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐹Gogithub.com/obot-platform/obotall versions0.21.1

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for github.com/obot-platform/obot. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.

  2. Fix

    Update github.com/obot-platform/obot to 0.21.1 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-vw82-7fv8-r6gp is resolved across your whole dependency graph.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

  4. How O3 protects you

    O3 pinpoints whether GHSA-vw82-7fv8-r6gp is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Tailored to GHSA-vw82-7fv8-r6gp. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

## Summary If you have the MCP Server ID, you can connect to the MCP server even if you don't have permissions to the server. The MCP gateway endpoint `/mcp-connect/{mcp_id}` does not enforce Access Control Rules (ACRs). Any authenticated Obot user who possesses an MCP Server ID can connect to that server through the gateway — including making tool calls — regardless of whether they are a member of any MCP Registry that grants access to the server. In practice this means any User can fully use MCP servers that the administrator believed were restricted to specific groups. ## Severity Repo
O3 Security · Impact-Aware SCA

Is GHSA-vw82-7fv8-r6gp in your dependencies?

O3 detects GHSA-vw82-7fv8-r6gp across Go dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.