GitHub Advisoryadvisory · PyPI
GHSA-98x5-vq43-vc5p semantic-router exposed to compromised litellm wheel (CVE-2026-42208) via unbounded transitive pin
CRITICAL
Official page ↗
- Ecosystem
- PyPI
- Packages
- semantic-router
- Severity
- Critical
- Weaknesses
- CWE-506
- Reviewed
- 2026-06-26
Affected packages
• PyPI semantic-router: >= 0.1.8, < 0.1.15 → fixed in 0.1.15
Description
Impact
semantic-router versions 0.1.8 through 0.1.14 declare `litellm>=1.61.3` with no upper bound. During the window in which `litellm==1.82.8` was the latest release on PyPI, a fresh install of any affected semantic-router version could resolve to that compromised wheel.
The malicious `litellm==1.82.8` wheel ships a `litellm_init.pth` file that executes on Python interpreter startup — no import required. It collects and exfiltrates:
• Process environment variables
• AWS / GCP / Azure credentials
• SSH keys, Kubernetes configs, shell history
• Database credentials and CI/CD secrets
• Cryptocurrency wallets
Stage-two payload encrypts the collected data (AES-256 + embedded RSA pubkey) and POSTs it to `https://models.litellm.cloud/`.
See upstream: BerriAI/litellm#24512 and CVE-2026-42208.
Patches
Fixed in semantic-router 0.1.15, which raises the floor to `litellm>=1.83.7`.
Workarounds
If developers cannot upgrade immediately:
• Pin `litellm>=1.83.7,!=1.82.8` explicitly in their own project.
• Audit `site-packages/` for `litellm_init.pth` and delete if present.
• Rotate any credentials reachable from environments where an affected install ran.
Credit
Upstream report and triage by the litellm maintainers — see issue #24512.
One caveat before publishing
CVE-2026-42208 specifically names 1.82.8. Pip's resolver picks "latest matching", so the real affected blast radius for semantic-router is users who ran pip install during the window that 1.82.8 was on PyPI — not everyone who ever installed 0.1.8–0.1.14. The advisory is still correct (an affected install could have pulled the bad wheel), but consider whether a Severity: Critical / Exploitability: time-bounded note would help downstream readers understand the exposure model.
Related
Weakness · CWE (1)
- CWE-506 Embedded Malicious Code weakness