This release includes 1 breaking change for platform teams planning a safe upgrade.
✓ No known CVEs patched in this version
Topics
+14 more
Summary
AI summaryRemoved _meta.tools from mcp-registry server.json.
Full changelog
What's Changed
- feat: ResponseInspector — cloaking, SVG, invisible char detection (#241) by @msaad00 in https://github.com/msaad00/agent-bom/pull/284
- fix: reduce SKILL.md surface area for OpenClaw trust score by @msaad00 in https://github.com/msaad00/agent-bom/pull/285
- refactor: split OpenClaw SKILL.md into 4 focused skills by @msaad00 in https://github.com/msaad00/agent-bom/pull/287
- feat: ARCHITECTURE.md + expand SAST CWE map (10 → 52) by @msaad00 in https://github.com/msaad00/agent-bom/pull/303
- feat: MITRE ATT&CK mapping + Azure/GCP CIS benchmarks + ML model provenance by @msaad00 in https://github.com/msaad00/agent-bom/pull/308
- feat: MAESTRO layer tagging + vector DB scanning + AISVS v1.0 compliance by @msaad00 in https://github.com/msaad00/agent-bom/pull/312
- chore: pin docs.yml action versions to SHAs by @msaad00 in https://github.com/msaad00/agent-bom/pull/313
- fix: improve OpenClaw trust score — accurate credential claims + verification guidance by @msaad00 in https://github.com/msaad00/agent-bom/pull/314
- refactor: consolidate OpenClaw skills into one comprehensive SKILL.md by @msaad00 in https://github.com/msaad00/agent-bom/pull/315
- chore: fix stale doc claims before release (20→22 tools, 6100→3400 tests) by @msaad00 in https://github.com/msaad00/agent-bom/pull/316
- feat: ClusterFuzzLite integration + README accuracy fixes by @msaad00 in https://github.com/msaad00/agent-bom/pull/317
- feat: add OpenSSF Best Practices passing badge (100%) by @msaad00 in https://github.com/msaad00/agent-bom/pull/318
- chore: bump version to v0.60.0 by @msaad00 in https://github.com/msaad00/agent-bom/pull/319
- fix: remove _meta.tools from mcp-registry server.json by @msaad00 in https://github.com/msaad00/agent-bom/pull/320
- feat: cache poisoning + cross-agent injection detection by @msaad00 in https://github.com/msaad00/agent-bom/pull/321
- feat: cross-agent lateral movement visualization in attack flow by @msaad00 in https://github.com/msaad00/agent-bom/pull/322
- feat: Databricks Security Best Practices checks by @msaad00 in https://github.com/msaad00/agent-bom/pull/324
- chore: codebase audit fixes + AUDIT.md by @msaad00 in https://github.com/msaad00/agent-bom/pull/325
- fix: wire VectorDBInjectionDetector into proxy + runtime audit by @msaad00 in https://github.com/msaad00/agent-bom/pull/326
- fix: avoid duplicate injection alerts for non-vector tools in proxy by @msaad00 in https://github.com/msaad00/agent-bom/pull/327
- chore: final audit pass — accuracy, SVGs, CLI parity by @msaad00 in https://github.com/msaad00/agent-bom/pull/328
- fix: O1 NVIDIA bundling coverage, O2 ecosystem fixtures, O5 guard docs by @msaad00 in https://github.com/msaad00/agent-bom/pull/329
- chore: make analytics — adoption metrics snapshot (PyPI + GitHub traffic) by @msaad00 in https://github.com/msaad00/agent-bom/pull/333
- fix: CLI quality — OSV vuln enrichment, --version, first-run UX, error handler by @msaad00 in https://github.com/msaad00/agent-bom/pull/334
- fix: P0 — ecosystem case normalization, OSV detail enrichment, zero test failures by @msaad00 in https://github.com/msaad00/agent-bom/pull/335
- chore: bump version to v0.60.1 by @msaad00 in https://github.com/msaad00/agent-bom/pull/336
Full Changelog: https://github.com/msaad00/agent-bom/compare/v0.59.3...v0.60.1
Breaking Changes
- Removed _meta.tools from mcp-registry server.json
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]