This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+14 more
Affected surfaces
Summary
AI summaryAdded MCP supply chain security features, cost management enhancements, and multi‑agent governance capabilities.
Full changelog
What's New in v0.3.0
MCP Supply Chain Security
- Tool poisoning detection: 10 regex patterns against Unicode-normalized text, schema recursion
- Rug pull detection: SHA-256 hash pinning, definition change alerts
- Argument sanitization: Path traversal, command injection, null byte detection
- Trust scoring (L0-L4): Automated trust levels from scan + pin + audit status
- Vulnerability database: 8 built-in CVEs for popular MCP servers, version-range matching, auto-block
- SBOM generation: CycloneDX-inspired bill of materials with vulnerability overlay
Cost Management
- Cost circuit breaker: 17 model pricing entries, loop detection, hierarchical budgets, thread-safe
- Cross-framework cost tracking: LangChain + OpenAI + Anthropic + Google → unified CostTracker
- Multi-agent cost attribution: Delegation trees, subtree rollup, formatted attribution reports
Multi-Agent Governance
- A2A communication governance: Capability-gated messaging, PII/credential redaction, rate limiting, audit log
- Session replay: Record/replay agent sessions with retroactive security scanning (20 patterns)
Observability
- OpenTelemetry export: Policy/cost/anomaly/MCP events → OTel spans, in-memory fallback
- Policy-as-code Git integration: Diff formatting, impact analysis, drift detection, YAML export
Changed
- Development status upgraded from Alpha to Beta
- PyPI keywords expanded (mcp, cost-management, supply-chain-security, a2a, observability)
Stats
- 2,238+ tests passing
- 92% code coverage
pip install agent-aegis==0.3.0
Full changelog: https://github.com/Acacian/aegis/blob/main/CHANGELOG.md
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]