Summary
acgs v was classified as CRITICAL RISK with a risk score of 1739. Sigil detected 189 findings across 205 files, covering phases including network exfiltration, code patterns, obfuscation, credential access. Review the findings below before installing this package.
Package description: Constitutional AI governance for any agent. Wrap any LLM agent in enforceable rules, audit trails, and separation of powers — in 5 lines of code.
v
21 March 2026, 12:02 UTC
by Sigil Bot
Risk Score
1739
Findings
189
Files Scanned
205
Provenance
Registry
https://pypi.org/project/acgs/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/1122CB28-F77C-499D-BC17-BA8D125E84F3)HTML
<a href="https://sigilsec.ai/scans/1122CB28-F77C-499D-BC17-BA8D125E84F3"><img src="https://sigilsec.ai/badge/pypi/acgs" 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.