registry / @steipete/summarize / 0.20.1

@steipete/summarize@0.20.1

Link → clean text → summary.

AI Security Review

scanned 4h 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 `summarize daemon install --token …` and uses the daemon/agent workflow.

Impact

A holder of the daemon token can invoke its local agent capabilities; stored provider credentials increase local compromise impact.

Mechanism

Persistent localhost daemon with LLM-directed browser automation and stored runtime environment snapshot.

Rationale

The package is not malicious by the inspected source, but it ships a persistent, credential-bearing LLM/browser-automation daemon with an eval-capable fallback. Downgrade to a warning for dangerous dual-use capability and explicit persistence, not a publish block.

Evidence

package.jsondist/cli.jsdist/esm/daemon/cli.jsdist/esm/daemon/env-snapshot.jsdist/esm/daemon/server-auth.jsdist/esm/daemon/constants.jsdist/esm/daemon/agent.jsdist/esm/daemon/agent-request.js~/.summarize/daemon.json~/.config/systemd/user/summarize-daemon.service~/Library/LaunchAgents/com.steipete.summarize.daemon.plist~/.summarize/daemon.cmd~/.summarize/daemon-launch.vbs

@steipete/summarize@0.20.1

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code