# DeepTutor missing MCP tool authorization allows non-admin users to invoke unrestricted tools

Advisory record · `GHSA-jg88-rvpc-qvxj`

- **Identifiers:** `GHSA-jg88-rvpc-qvxj` · `CVE-2026-58168` · `PYSEC-2026-4206`
- **State:** Confirmed
- **Severity:** CVSS 7.7 High
- **Critical:** No
- **Weakness (CWE):** [CWE-862](https://cwe.mitre.org/data/definitions/862.html)
- **Tags:** [Broken access control](https://agentprime.io/advisories/tag/access-control.md)
- **Published:** 30 Jun 2026
- **Updated:** 15 Oct 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 30 Jun 2026, 18:31 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `deeptutor` (PyPI): affected `<1.4.10`; fixed in `1.4.10`

## Machine-written summary

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

> DeepTutor versions before 1.4.10 are affected by an authorization bypass: when a user's grant omits MCP tools, the access check returns no result instead of denying access, so low-privilege users can invoke any configured MCP tool. An attacker with a user session, or prompt-injected content acting within one, could enumerate and call tools such as filesystem, shell, and browser servers. Upgrade to version 1.4.10 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

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

- **CISA KEV:** Not listed.
- **EPSS:** 0.0041, the 36th percentile, on 18 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 30 Jun 2026, 15:52 UTC: [Confirmed by the CVE List](https://www.cve.org/CVERecord?id=CVE-2026-58168)
- 31 Oct 2026, 14:08 UTC: First seen by agentprime
- 31 Oct 2026, 14:08 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-jg88-rvpc-qvxj)

## Sources

- [GitHub Advisory Database: GHSA-jg88-rvpc-qvxj](https://github.com/advisories/GHSA-jg88-rvpc-qvxj)
- [OSV: GHSA-jg88-rvpc-qvxj](https://osv.dev/vulnerability/GHSA-jg88-rvpc-qvxj)
- <https://nvd.nist.gov/vuln/detail/CVE-2026-58168>
- <https://github.com/HKUDS/DeepTutor/pull/579>
- <https://github.com/HKUDS/DeepTutor/commit/90046374b3dcd4f8a866d2d64a64440bc08eb2ef>
- <https://github.com/HKUDS/DeepTutor>
- <https://github.com/HKUDS/DeepTutor/releases/tag/v1.4.10>
- <https://www.vulncheck.com/advisories/deeptutor-insecure-default-grants-unrestricted-mcp-tool-access-to-non-admin-users>

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-jg88-rvpc-qvxj>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-jg88-rvpc-qvxj/>. Everything for agents: <https://agentprime.io/llms.txt>.
