registry / rethread / 0.2.0

rethread@0.2.0

Portable, token-bounded handoffs between Claude Code, Codex, and Antigravity when an AI coding subscription hits its quota.

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 accepts the interactive hook prompt or runs `rethread hooks install`.

Impact

Persistent agent hooks can collect local workflow context on agent lifecycle events.

Mechanism

User-authorized AI-agent hook installation and local context capture.

Rationale

This is an explicit-user-command mutation of AI-agent configuration with local data capture, so it warrants a warning under policy. Source inspection found no unconsented install hook, remote execution, or exfiltration.

Evidence

package.jsonsrc/commands/init.mjssrc/core/hooks.mjssrc/core/shell.mjssrc/commands/checkpoint.mjssrc/core/redact.mjs~/.claude/settings.json~/.codex/hooks.json.rethread/handoffs/*.json.rethread/handoffs/*.md

Decision evidence

public snapshot

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

rethread@0.2.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code