registry / @twofive/snail-pi-web / 0.7.3

@twofive/snail-pi-web@0.7.3

Snail Pi Web (蜗牛派) workspace for the pi coding agent

AI Security Review

scanned 3h 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 `spi` and uses its local web API/UI features.

Impact

A user or party able to access the running local service can cause commands, package installation, and Pi-agent configuration changes through exposed features.

Mechanism

Local web-mediated terminal execution, Pi configuration writes, and `npx` skill installation.

Rationale

This is not malicious by source evidence, but it ships substantial user-triggered agent and shell capabilities behind a local web service. Per firewall policy, that unresolved dangerous dual-use surface warrants a warning rather than a block.

Evidence

package.jsonREADME.mdbin/pi-web.jsscripts/build-next.jsscripts/start-pi-web-proxy.shscripts/start-pi-web-proxy.ps1next.config.ts.next/server/app/api/terminal/sessions/route.js.next/server/app/api/skills/install/route.js.next/server/app/api/subagents/config/route.js~/.pi/agent/

Network endpoints1

@twofive/snail-pi-web@0.7.3

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code