Summary
kalibr v1.9.0 was classified as CRITICAL RISK with a risk score of 113. Sigil detected 15 findings across 94 files, covering phases including network exfiltration, code patterns, provenance. Review the findings below before installing this package.
Package description: Outcome-aware LLM routing for production AI agents. Routes between models, tools, and parameters based on real success signals using Thompson Sampling. Automatic fallback, cost optimization, and co...
v1.9.0
27 March 2026, 07:33 UTC
by Sigil Bot
Risk Score
113
Findings
15
Files Scanned
94
Provenance
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
[](https://sigilsec.ai/scans/7694F9AC-2E26-4A85-9575-864530E18349)HTML
<a href="https://sigilsec.ai/scans/7694F9AC-2E26-4A85-9575-864530E18349"><img src="https://sigilsec.ai/badge/pypi/kalibr" alt="Sigil Scan"></a>Run This Scan Yourself
Scan your own packages
Run Sigil locally to audit any package before it touches your codebase.
Early Access
Get cloud scanning, threat intel, and CI/CD integration.
Join 150+ developers on the waitlist.
Get threat intelligence and product updates
Security research, new threat signatures, and product updates. No spam.
Other pypi scans
Believe this result is incorrect? Request a review or see our Terms of Service and Methodology.