This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+14 more
Summary
AI summaryConsolidated IA hub, scalable graph view without pagination, and improved repository README accuracy.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Adds readable-at-scale unified graph with auto-layout and clustering. Adds readable-at-scale unified graph with auto-layout and clustering. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Feature | Medium |
Consolidates Connections, Cloud, and Data-sources into a single hub. Consolidates Connections, Cloud, and Data-sources into a single hub. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Feature | Medium |
Introduces unified Asset Inventory section. Introduces unified Asset Inventory section. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Feature | Low |
Implements bounded retention with default ~90‑day time‑window filters. Implements bounded retention with default ~90‑day time‑window filters. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Performance | Low |
Improves findings sorting via index‑backed unfiltered effective‑reach and materialized trust score. Improves findings sorting via index‑backed unfiltered effective‑reach and materialized trust score. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Bugfix | Medium |
Fixes Codex‑flagged correctness bugs in audit: skill false positives, traversal OOM, nested‑worktree recursion, --no-ui handling, and startup auth logging. Fixes Codex‑flagged correctness bugs in audit: skill false positives, traversal OOM, nested‑worktree recursion, --no-ui handling, and startup auth logging. Source: llm_adapter@2026-07-16 Confidence: high |
— |
Full changelog
What's Changed
- chore(repo): README self-host + accuracy, Pages concurrency fix, contributor identity cleanup by @msaad00 in https://github.com/msaad00/agent-bom/pull/4043
- feat(graph): readable-at-scale unified graph — auto-layout, clustering, no pagination by @msaad00 in https://github.com/msaad00/agent-bom/pull/4045
- feat(ia): consolidate Connections/Cloud/Data-sources into one hub by @msaad00 in https://github.com/msaad00/agent-bom/pull/4047
- feat(inventory): unified Asset Inventory section by @msaad00 in https://github.com/msaad00/agent-bom/pull/4046
- test(e2e): update connections screenshot spec for the consolidated hub by @msaad00 in https://github.com/msaad00/agent-bom/pull/4048
- fix(audit): Codex-flagged correctness bugs — skills FP, traversal OOM, nested-worktree recursion, --no-ui, startup auth log by @msaad00 in https://github.com/msaad00/agent-bom/pull/4050
- feat(scale): bounded retention + default ~90d time-window filters by @msaad00 in https://github.com/msaad00/agent-bom/pull/4052
- perf(findings): index-backed unfiltered effective-reach sort + trust materialized score by @msaad00 in https://github.com/msaad00/agent-bom/pull/4054
- chore(release): 0.96.3 by @msaad00 in https://github.com/msaad00/agent-bom/pull/4056
Full Changelog: https://github.com/msaad00/agent-bom/compare/v0.96.2...v0.96.3
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 msaad00/agent-bom
AI supply chain security scanner with 18 MCP tools. Auto-discovers 20 MCP clients, scans dependencies for CVEs (OSV/NVD/EPSS/CISA KEV), maps blast radius from vulnerabilities to exposed credentials and tools, runs CIS benchmarks, generates CycloneDX/SPDX SBOMs, and enforces compliance across OWASP LLM Top 10, MITRE ATLAS, NIST AI RMF, and EU AI Act.
Related context
Related tools
Beta — feedback welcome: [email protected]