registry / @kaiquegazola/ralphrun / 0.2.0

@kaiquegazola/ralphrun@0.2.0

CLI-agnostic autonomous build loop — fresh context per task, executor + advisor. Inspired by snarktank/ralph.

AI Security Review

scanned 8h 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 `ralphrun` with a PRD/configuration.

Impact

Configured agents and verification commands can modify or execute within the user-selected workspace with reduced safeguards.

Mechanism

Autonomous agent orchestration with approval-bypass command adapters and user-defined shell verification.

Rationale

Source inspection found no malicious lifecycle, exfiltration, remote payload, or stealth behavior. The explicit approval-bypass agent orchestration and shell-based PRD verification warrant a warning as a dangerous capability.

Evidence

package.jsondist/index.jsdist/chunk-EGUBATUM.jsdist/chunk-3YRHEMGR.js

Decision evidence

public snapshot

AI called this Suspicious at 91.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

`dist/chunk-EGUBATUM.js` builds Codex commands with approval, sandbox, and hook-trust bypass flags.

@kaiquegazola/ralphrun@0.2.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code