Skip to content

msaad00/agent-bom

v0.70.7 Breaking

This release includes breaking changes for platform teams planning a safe upgrade.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai-agents ai-security ai-supply-chain aibom blast-radius cloud-security
+14 more
compliance container-security cyclonedx security kubernetes llm-security mcp mcp-server owasp sarif sbom security-scanner supply-chain-security vulnerability-scanning

Summary

AI summary

Added AI component source scanning, DeepSeek detection, and multiple new output formats.

Full changelog

What's Changed

  • fix: self-scan workflows use wrong CLI flags by @msaad00 in https://github.com/msaad00/agent-bom/pull/695
  • chore: reorganize repo root — 19 dirs → 11, 38 files → 20 by @msaad00 in https://github.com/msaad00/agent-bom/pull/697
  • fix: SEVERITY_ORDER missing UNKNOWN + CVSS 0.0 → none by @msaad00 in https://github.com/msaad00/agent-bom/pull/715
  • fix: SARIF security-severity property + UNKNOWN→note by @msaad00 in https://github.com/msaad00/agent-bom/pull/716
  • feat: GitHub Action — 5 improvements (output, warn, auto-db, PR comment, badge) by @msaad00 in https://github.com/msaad00/agent-bom/pull/717
  • feat: CLI scan — --db-source, --auto-update-db=ON, --offline by @msaad00 in https://github.com/msaad00/agent-bom/pull/718
  • feat: MCP scan — auto_update_db, db_sources, format + isError pattern by @msaad00 in https://github.com/msaad00/agent-bom/pull/719
  • fix: Docker SSE healthcheck, policy field validation, expanded dogfood CI by @msaad00 in https://github.com/msaad00/agent-bom/pull/720
  • fix: scanner core gaps — conda resolution, npm semver, SARIF enrichment by @msaad00 in https://github.com/msaad00/agent-bom/pull/731
  • feat: CWE enrichment — OSV extraction, universal compliance tagging, DB schema v2 by @msaad00 in https://github.com/msaad00/agent-bom/pull/734
  • fix: ClawHub skill accuracy — resolve compliance contradictions, align metadata by @msaad00 in https://github.com/msaad00/agent-bom/pull/735
  • feat: add JUnit XML, CSV, and Markdown output formats by @msaad00 in https://github.com/msaad00/agent-bom/pull/743
  • release: v0.70.7 — AI BOM positioning, output formats, README revamp by @msaad00 in https://github.com/msaad00/agent-bom/pull/744
  • feat: AI component source scanning — detect SDK imports, shadow AI, deprecated models by @msaad00 in https://github.com/msaad00/agent-bom/pull/745
  • feat: DeepSeek detection + GlassWorm invisible Unicode defense by @msaad00 in https://github.com/msaad00/agent-bom/pull/746
  • feat: AI inventory Rich table + JSON/HTML/SARIF export by @msaad00 in https://github.com/msaad00/agent-bom/pull/747
  • fix: AI inventory end-to-end in CLI output by @msaad00 in https://github.com/msaad00/agent-bom/pull/748
  • feat: CLI UX — progress bar, timing breakdown, next-steps suggestions by @msaad00 in https://github.com/msaad00/agent-bom/pull/749
  • fix: update MCP tool count 31→32 across all surfaces by @msaad00 in https://github.com/msaad00/agent-bom/pull/750
  • fix: deploy-mcp-sse checkout release tag + freshness guard by @msaad00 in https://github.com/msaad00/agent-bom/pull/751
  • chore: v0.70.7 demo GIF + version alignment by @msaad00 in https://github.com/msaad00/agent-bom/pull/752

Full Changelog: https://github.com/msaad00/agent-bom/compare/v0...v0.70.7

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

Track msaad00/agent-bom

Get notified when new releases ship.

Sign up free

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.

All releases →

Related context

Beta — feedback welcome: [email protected]