Summary
kumagallium/crucible-agent v2026-03-19 was classified as CRITICAL RISK with a risk score of 56. Sigil detected 11 findings across 54 files, covering phases including provenance, credential access, network exfiltration. Review the findings below before installing this package.
Package description: AI agent runtime that connects any frontend to MCP servers via LLM — domain behavior is driven by swappable prompt profiles
v2026-03-19
20 March 2026, 00:44 UTC
by Sigil Bot
Risk Score
56
Findings
11
Files Scanned
54
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/66B05B4C-03C7-4734-8D90-EBA2A860B3DB)HTML
<a href="https://sigilsec.ai/scans/66B05B4C-03C7-4734-8D90-EBA2A860B3DB"><img src="https://sigilsec.ai/badge/github/kumagallium/crucible-agent" 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 github scans
Believe this result is incorrect? Request a review or see our Terms of Service and Methodology.