Skip to content

Jovancoding/Network-AI

v5.5.4 Maintenance

This release keeps dependencies and maintenance posture current for teams operating this tool.

Published 17d MCP Developer Tools
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-framework agent-orchestration ai-agents autogen blackboard blackboard-architecture
+14 more
crewai hermes hermes-agent langchain llm mcp multi-agent nemoclaw nodejs openclaw orchestration rlm typescript workflow-engine

Affected surfaces

auth rbac

Summary

AI summary

Minor fixes and improvements.

Changes in this release

Security Medium

Column renamed: Confidence → Severity in SKILL.md Security Scan Findings table.

Column renamed: Confidence → Severity in SKILL.md Security Scan Findings table.

Source: granite4.1:8b-q6_K@2026-05-21

Confidence: high

Security Medium

ASI03 advisory tokens severity changed from High to Medium for v5.5.3 scan results.

ASI03 advisory tokens severity changed from High to Medium for v5.5.3 scan results.

Source: granite4.1:8b-q6_K@2026-05-21

Confidence: high

Security Medium

ASI06 project context severity changed from High to Medium for v5.5.3 scan results.

ASI06 project context severity changed from High to Medium for v5.5.3 scan results.

Source: granite4.1:8b-q6_K@2026-05-21

Confidence: high

Security Medium

New Low ASI03 advisory: .signing_key and active_grants.json are security-relevant local state; mitigate by keeping data/ private and restricting OS permissions on shared machines.

New Low ASI03 advisory: .signing_key and active_grants.json are security-relevant local state; mitigate by keeping data/ private and restricting OS permissions on shared machines.

Source: granite4.1:8b-q6_K@2026-05-21

Confidence: low

Security Medium

New Low ASI06 advisory: justification fields and data/audit_log.jsonl store agent-provided free text locally; avoid including PII, secrets, or credentials; restrict data/ directory on shared machines.

New Low ASI06 advisory: justification fields and data/audit_log.jsonl store agent-provided free text locally; avoid including PII, secrets, or credentials; restrict data/ directory on shared machines.

Source: granite4.1:8b-q6_K@2026-05-21

Confidence: low

Feature Medium

SECURITY.md updated to summarise v5.5.3 ClawHub scanner state (2 Medium, 2 Low findings).

SECURITY.md updated to summarise v5.5.3 ClawHub scanner state (2 Medium, 2 Low findings).

Source: granite4.1:8b-q6_K@2026-05-21

Confidence: high

Deprecation Medium

All four remaining ClawHub scan findings are acknowledged as by design with documented controls in SKILL.md.

All four remaining ClawHub scan findings are acknowledged as by design with documented controls in SKILL.md.

Source: granite4.1:8b-q6_K@2026-05-21

Confidence: low

Full changelog

What's changed

Documentation — ClawHub scan findings

Updated SKILL.md Security Scan Findings table to reflect the v5.5.3 ClawHub scan results:

  • Column renamed: ConfidenceSeverity (matches ClawHub UI terminology)
  • ASI03 advisory tokens: severity High → Medium
  • ASI06 project context: severity High → Medium
  • New — Low ASI03 local grant state: the .signing_key and active_grants.json files introduced in v5.5.2 are security-relevant local state; mitigation: keep data/ private, restrict OS-level permissions on shared machines
  • New — Low ASI06 audit log free text: justification fields and data/audit_log.jsonl store agent-provided free text locally — do not include PII, secrets, or credentials; restrict data/ directory on shared machines

All four remaining findings are by design. The documented controls in SKILL.md are the mitigations — not an elimination of the patterns.

SECURITY.md ClawHub scanner entry updated to summarise the v5.5.3 scan state (2 Medium, 2 Low, all acknowledged).


Full changelog: https://github.com/Jovancoding/Network-AI/blob/main/CHANGELOG.md

Documentation-only release. No code changes.

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 Jovancoding/Network-AI

Get notified when new releases ship.

Sign up free

About Jovancoding/Network-AI

Multi-agent orchestration MCP server with race-condition-safe shared blackboard. 20+ MCP tools: blackboard read/write, agent spawn/stop, FSM transitions, budget tracking, token management, and audit log query. `npx network-ai-server --port 3001`.

All releases →

Beta — feedback welcome: [email protected]