registry / @specdrive/core / 0.1.8

@specdrive/core@0.1.8

SpecDrive core domain model, spec engine, and knowledge base

AI Security Review

scanned 16h 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

Caller invokes installSpecdriveMcp, setupMcpIntegration, setupCursorIntegration, or an LLM generation API.

Impact

Can alter opted-in AI-client configuration and expose caller-supplied prompts/project context to the selected provider.

Mechanism

Explicit MCP configuration and user-keyed LLM requests

Rationale

Not malicious: source shows no automatic installation-time behavior or concrete malicious chain. Warn because explicit agent-client configuration mutation and shell-profile credential loading are consequential capabilities.

Evidence

package.jsondist/index.jsdist/integrations/mcp-install-service.jsdist/integrations/mcp-setup-service.jsdist/integrations/cursor-setup-service.jsdist/infrastructure/shell-profile-env.js.specdrive/mcp.json.cursor/mcp.json.cursor/rules/specdrive-workflow.mdc.cursor/rules/specdrive-cheatsheet.mdc.cursor/skills/specdrive-sdd/SKILL.mdClaude/claude_desktop_config.json

Network endpoints

@specdrive/core@0.1.8

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code