registry / ion-code / 0.0.3

ion-code@0.0.3

Repository for ion-code coding agent

AI Security Review

scanned 19h 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 ion and submits a prompt.

Impact

A compromised or prompt-injected model session could execute commands or alter accessible files.

Mechanism

LLM-driven shell and filesystem agent

Rationale

No concrete malicious or install-time behavior was found. The package is a high-impact AI-agent tool with broad execution capability, so it warrants a warning rather than a publish block.

Evidence

package.jsondist/index.jsdist/agent/runner.jsdist/tools/bashTool.jsdist/utils/secretGuard.jsdist/config/modelsConfig.jsdist/tools/readTool.jsdist/tools/writeTool.js

Network endpoints1

localhost:1234/v1

Decision evidence

public snapshot

AI called this at 90.0% confidence with false-positive risk.

ion-code@0.0.3

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code