Acacian/aegis

v0.4.2 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 2mo MCP Security & Auth

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-security ai-agent-security ai-agents ai-governance ai-safety ai-security

+14 more

audit-trail compliance guardrails langchain llm-security mcp mcp-security model-context-protocol pii-detection policy-as-code policy-engine policy-testing prompt-injection selection-governance

Affected surfaces

auth rbac

Summary

AI summary

Toxicity guardrail default behavior changes from block to warn.

Full changelog

What's New

Constitutional Protocol (Phase 1 + 2)

Agent Constitution: Ontology + obligations + constraints for structural governance
Plan-level governance: Sequence pattern detection + cumulative risk thresholds
Governance Envelope: A2A messages carry sender credentials (SHA-256 signed) — like TLS certs for agents
Governance Handshake: 5-step constitutional compatibility verification before agent communication
Cross-session data leakage detection: 5 detectors for shared MCP servers correlating requests across tenants

Performance

Lazy imports: import aegis loads 20 modules instead of 67 (174ms → 87ms, 2x faster)

Positioning Update

Toxicity guardrail default changed from block to warn (opt-in to block)
Security guardrails (injection, PII) remain unchanged
Governs what agents do (actions, tool calls, data access), not what they say

Compliance

Dual-compliance mapping: EU AI Act + NIST AI RMF + SOC2 + ISO 42001 + OWASP Agentic Top 10
All 11 auto-instrumentation frameworks now marked Stable

Stats

3,265+ tests passing
27 files changed, +4,300 lines
ruff/mypy clean

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track Acacian/aegis

Get notified when new releases ship.

About Acacian/aegis

Policy-based governance for AI agent tool calls. YAML policies, approval gates, risk assessment, and audit logging. Cross-platform: LangChain, OpenAI, Anthropic, MCP.

All releases →