registry / @subtextdev/subtext-wizard / 0.1.6

@subtextdev/subtext-wizard@0.1.6

Set up Subtext session capture in your app using your own coding agent

AI Security Review

scanned 9h 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 `subtext-install` and confirms the agent/configuration setup, or supplies `--yes`.

Impact

Can edit the selected project and persist a Subtext MCP endpoint in the selected agent's configuration; this is a meaningful AI-agent capability change but is disclosed and user-triggered.

Mechanism

Autonomous coding-agent launch plus explicit Subtext MCP/plugin configuration.

Rationale

This is not concrete malicious behavior: all agent execution and MCP setup occur only after explicit user invocation and normally confirmation. It still warrants a warning because it intentionally performs persistent AI-agent configuration and can autonomously modify project files.

Evidence

package.jsondist/run.jsdist/agents/codex.jsdist/agents/claude-code.jsdist/agents/gemini.jsdist/pluginSetup.jsdist/bin.jsproject/.mcp.json~/.codex/config.toml~/.gemini/settings.json

Network endpoints3

auth.fullstory.comapi.fullstory.com

@subtextdev/subtext-wizard@0.1.6

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code