registry / @rexedv/agent-channel / 0.2.0

@rexedv/agent-channel@0.2.0

Set up and update RexedV MCP agent sessions in any project

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 login, setup, update, or agent.

Impact

A configured agent session may receive workflow input with Bash, Write, Edit, and Skill permissions for the Herdr channel.

Mechanism

Writes MCP/session configuration and provisions RexedV channel credentials.

Rationale

Source supports a warning for explicit agent configuration that can enable high-impact agent tools, not a malicious block. No concrete credential theft, remote payload execution, or unconsented lifecycle mutation was found.

Evidence

package.jsondist/server.jsdist/setup-53VA7Q3R.jsdist/update-NYNBIZ56.jsdist/chunk-BA2OG4ZN.jsdist/chunk-FXR5JMNU.js~/.config/rexedv/credentials.json<projectDir>/<selected-session>/.mcp.json<projectDir>/<selected-session>/.claude/settings.json<projectDir>/<selected-session>/.claude/skills/

Network endpoints2

api.rexedv.com/api/v1/api-keys/api/v1/agent-channels/provision

@rexedv/agent-channel@0.2.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code