# Obot: Server-Side Request Forgery via remote MCP server URL

Advisory record · `GHSA-jgh3-fggc-mcpm`

- **Identifiers:** `GHSA-jgh3-fggc-mcpm` · `CVE-2026-101064` · `GO-2026-6522`
- **State:** Confirmed
- **Severity:** CVSS 8.3 High
- **Critical:** No
- **Weakness (CWE):** [CWE-918](https://cwe.mitre.org/data/definitions/918.html) · [CWE-1188](https://cwe.mitre.org/data/definitions/1188.html)
- **Tags:** [Server-side request forgery (SSRF)](https://agentprime.io/advisories/tag/ssrf.md) · [CWE-1188](https://agentprime.io/advisories/tag/cwe-1188.md)
- **Published:** 18 Sept 2026
- **Updated:** 28 Sept 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 18 Sept 2026, 17:59 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `github.com/obot-platform/obot` (Go): affected `<0.23.0`; fixed in `0.23.0`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> Obot (github.com/obot-platform/obot) versions before 0.23.0 are vulnerable to server-side request forgery through the URL of a remote MCP server, which is fetched server-side without destination checks. An attacker with the Power User, Power User Plus, or Admin role who registers a remote MCP server can make Obot send requests to internal services and cloud metadata endpoints and read the responses. Upgrade to version 0.23.0 or later.

Written 1 Nov 2026.

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 8.3 High, CVSS 4.0: `CVSS:4.0/AV:N/AC:L/AT:N/PR:H/UI:N/VC:H/VI:L/VA:N/SC:H/SI:L/SA:N`, from CNA (VulnCheck)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0024, the 15th percentile, on 5 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 14:12 UTC: First seen by agentprime
- 31 Oct 2026, 14:12 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-jgh3-fggc-mcpm)

## Sources

- [GitHub Advisory Database: GHSA-jgh3-fggc-mcpm](https://github.com/advisories/GHSA-jgh3-fggc-mcpm)
- [OSV: GHSA-jgh3-fggc-mcpm](https://osv.dev/vulnerability/GHSA-jgh3-fggc-mcpm)
- <https://github.com/obot-platform/obot/security/advisories/GHSA-jgh3-fggc-mcpm>
- <https://github.com/obot-platform/obot>
- <https://github.com/obot-platform/obot/releases/tag/v0.23.0>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-jgh3-fggc-mcpm>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-jgh3-fggc-mcpm/>. Everything for agents: <https://agentprime.io/llms.txt>.
