Is llm-guard-kit safe to install?

llm-guard-kit was flagged as CRITICAL RISK (risk score 1360) with 136 findings detected across 253 files. Review the findings before installing.

What security issues were found in llm-guard-kit?

Sigil detected 136 findings in llm-guard-kit, including patterns related to code_patterns, network_exfil, obfuscation. See the full scan report for details.

Scans/pypi/llm-guard-kit

llm-guard-kit

pypi

Summary

llm-guard-kit v0.65.2 was classified as CRITICAL RISK with a risk score of 1360. Sigil detected 136 findings across 253 files, covering phases including code patterns, network exfiltration, obfuscation. Review the findings below before installing this package.

Package description: v0.65.2: README corrected — SC_OLD HP 0.817→0.625 (live chains), J5 Haiku fresh-holdout numbers, DomainRouter and cross-arch ensemble added to validated AUROC table.

CRITICAL RISK(1360)

v0.65.2

25 March 2026, 10:20 UTC

by Sigil Bot

Risk Score

1360

Findings

136

Files Scanned

253

Provenance

Registry

https://pypi.org/project/llm-guard-kit/0.65.2/

Findings by Phase

•

Phase Ordering

Phases are ordered by criticality, with the most dangerous at the top. Click any phase header to expand or collapse its findings. Critical phases are expanded by default.

Badge

Markdown

[![Sigil Scan](https://sigilsec.ai/badge/pypi/llm-guard-kit)](https://sigilsec.ai/scans/5BD7D93E-C0EE-4C2F-8F09-70F9010B96EF)

HTML

<a href="https://sigilsec.ai/scans/5BD7D93E-C0EE-4C2F-8F09-70F9010B96EF"><img src="https://sigilsec.ai/badge/pypi/llm-guard-kit" alt="Sigil Scan"></a>

Run This Scan Yourself