registry / @murrmure/cli / 1.0.0

@murrmure/cli@1.0.0

AI Security Review

scanned 3h 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 configures and runs `murrmure mcp` with MURRMURE_HUB_TOKEN and MURRMURE_SPACE_ID.

Impact

A trusted or compromised configured hub can direct the connected agent to use its existing workspace tools.

Mechanism

Authenticated hub polling relays remote control prompts into an MCP agent session.

Rationale

No malicious install-time mutation, credential exfiltration, or covert payload execution was found. The explicit MCP control channel is a dangerous capability that warrants a warning rather than a block.

Evidence

package.jsondist/cli.jsdist/chunk-W3U5GBR3.js.murrmure/pending-wake.json

Network endpoints2

127.0.0.1:8787/v1/mcp/catalog127.0.0.1:8787/v1/mcp/session/handshake

Decision evidence

public snapshot

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

@murrmure/cli@1.0.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code