This release adds 3 notable features for engineering teams evaluating rollout.
Published 2mo
MCP Security & Auth
✓ No known CVEs patched
✓ 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
Summary
AI summaryIntroduces natural language policy generation and adversarial policy probing.
Full changelog
What's New
Natural Language Policy Generation (aegis autopolicy)
- Generate YAML policies from plain English descriptions
- Tier 1: Built-in keyword parser (no dependencies)
- Tier 2: Pluggable LLM evaluator protocol (bring your own API key)
- Parses conditions: amount thresholds, time restrictions, weekday limits, target detection
Adversarial Policy Probe (aegis probe)
- Automated testing for governance gaps
- 6 probe categories: missing coverage, glob bypass, default fallthrough, escalation, target gaps, wildcard rules
- Robustness score (0-100) with detailed findings and recommendations
MCP Server Remote Transport
- SSE and Streamable HTTP transport support
aegis-mcp-server --transport sse --port 8080for remote access- Enables Glama connectors registration
Other
- Dockerfile for Glama MCP server deployment
- Streamlit demo app with real OpenAI function calling (examples/awesome-llm-apps/)
- README: enterprise features, updated architecture and roadmap
- 92 new tests (1,734 total)
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
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.
Related context
Beta — feedback welcome: [email protected]