registry / myminicode / 1.0.5

myminicode@1.0.5

A minimal terminal coding agent powered by an LLM.

AI Security Review

scanned 14h 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 minicode and submits a task.

Impact

An untrusted prompt/model response could modify the user workspace or run commands; unsandboxed execution requires an explicit environment override.

Mechanism

LLM-directed workspace tools and sandboxed shell execution

Rationale

Not malicious: source shows no lifecycle execution, stealth persistence, or unconsented exfiltration. Warn because it is a networked AI coding agent with consequential user-invoked file and command capabilities.

Evidence

package.jsondist/index.jsdist/chunk-LIWUBNXR.jsdist/chunk-4KXRHSS2.js

Network endpoints4

openrouter.ai/api/v1api.mistral.ai/v1r.jina.ai/s.jina.ai/

Decision evidence

public snapshot

myminicode@1.0.5

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code