# semantic-router exposed to compromised litellm wheel (CVE-2026-42208) via unbounded transitive pin

Advisory record · `GHSA-98x5-vq43-vc5p`

- **Identifiers:** `GHSA-98x5-vq43-vc5p`
- **State:** Confirmed
- **Severity:** No CVSS score
- **Critical:** No
- **Weakness (CWE):** [CWE-506](https://cwe.mitre.org/data/definitions/506.html)
- **Tags:** [CWE-506](https://agentprime.io/advisories/tag/cwe-506.md)
- **Published:** 26 Jun 2026
- **Updated:** 26 Jun 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 26 Jun 2026, 20:51 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `semantic-router` (PyPI): affected `>=0.1.8, <0.1.15`; fixed in `0.1.15`

## 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

No source has published a CVSS score for this record yet.

- **CISA KEV:** Not listed.
- **EPSS:** No score.

## Timeline

This record came from the full history of the GitHub Advisory Database, published 26 Jun 2026. New records show when each source confirmed them.

## Sources

- [GitHub Advisory Database: GHSA-98x5-vq43-vc5p](https://github.com/advisories/GHSA-98x5-vq43-vc5p)
- [OSV: GHSA-98x5-vq43-vc5p](https://osv.dev/vulnerability/GHSA-98x5-vq43-vc5p)
- <https://github.com/aurelio-labs/semantic-router/security/advisories/GHSA-98x5-vq43-vc5p>
- <https://github.com/aurelio-labs/semantic-router>

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-98x5-vq43-vc5p>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-98x5-vq43-vc5p/>. Everything for agents: <https://agentprime.io/llms.txt>.
