# three-typosquatted-ai-labs-sdk-pypi-packages-exfiltrate-developer: Three Typosquatted "AI Labs SDK" PyPI Packages Exfiltrate Developer Reconnaissance Data

> Three Typosquatted "AI Labs SDK" PyPI Packages Exfiltrate Developer Reconnaissance Data is a high-severity supply chain compromise issue in "AI Labs SDK" PyPI packages, an AI agent. Affected: "AI Labs SDK" PyPI packages (3 names, removed within 24h of May 19).

- **Canonical URL:** https://catalog.anomity.ai/vuln/three-typosquatted-ai-labs-sdk-pypi-packages-exfiltrate-developer
- **Aliases:** ti-029
- **Severity:** high
- **Attack type:** Supply chain compromise
- **Component:** "AI Labs SDK" PyPI packages (AI agent)
- **Exploited in the wild:** no known exploitation
- **Published:** 2026-05-19
- **Last verified:** 2026-11-01
- **JSON:** https://catalog.anomity.ai/api/entries/vuln/three-typosquatted-ai-labs-sdk-pypi-packages-exfiltrate-developer

## Summary

Three malicious packages typosquatting AI Labs were published to PyPI on May 19 and available for less than 24 hours, accumulating ~1,600 installs. The packages contained no actual SDK functionality, only reconnaissance code that exfiltrated hostname, username, installed Python packages, presence of cloud-credential files, and the listing of ~/.config and project root contents to an attacker-controlled server. The recon profile suggests a follow-on targeted attack on the harvested machines.

## Affected versions

| Affected | Fixed in |
| --- | --- |
| "AI Labs SDK" PyPI packages (3 names, removed within 24h of May 19) | no fixed version listed |

## Am I affected by this vulnerability?

You are affected if you run "AI Labs SDK" PyPI packages (3 names, removed within 24h of May 19).

## How do I fix it?

Audit pip install history on developer machines for AI Labs / ai-labs-sdk style names installed May 19. Block typosquatting via PyPI mirror with allowlisted package names. Treat any machine that installed one of these packages as compromised and rotate local cloud credentials.

## How do I find every machine running "AI Labs SDK" PyPI packages?

Anomity inventories the AI agents, MCP servers, IDE extensions and skills on each developer device, so you can see which machines run "AI Labs SDK" PyPI packages and which version, then enforce a policy on it.

## References

- article: https://www.reversinglabs.com/blog/malicious-attack-method-on-hosted-ml-models-now-targets-pypi

## Related vulnerabilities

- [load-mine-31-fake-qwen2-repositories-on-hugging-face-and-modelscope](https://catalog.anomity.ai/vuln/load-mine-31-fake-qwen2-repositories-on-hugging-face-and-modelscope) — high
- [microsoft-china-aligned-storm-0940-ran-the-artex-agentic-pen-test](https://catalog.anomity.ai/vuln/microsoft-china-aligned-storm-0940-ran-the-artex-agentic-pen-test) — high
- [slugfest-npm-trusted-publishing-bound-packages-to-reclaimable-github](https://catalog.anomity.ai/vuln/slugfest-npm-trusted-publishing-bound-packages-to-reclaimable-github) — high
- [GHSA-632h-h47v-g4x4](https://catalog.anomity.ai/vuln/ghsa-632h-h47v-g4x4) — high
- [plugin4shell-sha-pinning-bypass-gives-zero-click-rce-across-claude-code](https://catalog.anomity.ai/vuln/plugin4shell-sha-pinning-bypass-gives-zero-click-rce-across-claude-code) — critical
- [mandiant-hijacked-ai-coding-assistant-session-deploys-shai-hulud-across](https://catalog.anomity.ai/vuln/mandiant-hijacked-ai-coding-assistant-session-deploys-shai-hulud-across) — critical

---

Source: Anomity Security Database (https://catalog.anomity.ai/vuln). Detect affected AI tools on developer devices: https://anomity.ai/?utm_source=catalog&utm_medium=vuln-md&utm_campaign=three-typosquatted-ai-labs-sdk-pypi-packages-exfiltrate-developer