registry / @focuslabs/leyline / 0.1.1

@focuslabs/leyline@0.1.1

Meta-harness for Kiro — agent orchestration, persistent memory, task coordination, and self-learning capabilities

AI Security Review

scanned 2h ago · by lpm-firewall-ai

Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.

Static reason

No blocking static signals were detected.

Trigger

User runs `leyline init`; MCP runtime starts only through the configured/user-invoked `leyline mcp start`.

Impact

A consenting user can add configured agent capabilities and persistent project-local coordination state.

Mechanism

Explicit Kiro agent-extension setup with local `.leyline` state persistence.

Rationale

No evidence supports classifying the package as malicious. Its explicit AI-agent setup warrants a warning because it provisions agent capabilities and MCP configuration.

Evidence

package.jsonbin/leyline.jsdist/cli.jsdist/commands/init.jsdist/templates/agents.jsdist/templates/mcp-config.jsdist/services/memory.jsdist/services/vector/providers/openai.jsdist/mcp/server.jsdist/mcp/tools/system-tools.js.kiro/settings/mcp.json.kiro/agents/leyline-coder.json.kiro/agents/leyline-tester.json.kiro/agents/prompts/orchestrator.md.kiro/skills/memory-management/SKILL.md

@focuslabs/leyline@0.1.1

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code