@mulmoclaude/core@1.13.0
Shared server-side core for MulmoClaude and MulmoTerminal — the always-shipped-together subsystems consolidated behind subpath exports so the two hosts can't drift. Server-only except the browser-safe ./artifacts, ./whisper/client, ./workspace-setup/slug,
AI Security Review
scanned 3mo ago · by lpm-firewall-aiThe package is not malicious by source evidence, but its guarded runtime management of active Claude skills is a meaningful agent-extension control surface under the firewall policy.
Decision evidence
public snapshot- dist/skill-bridge/index.js mirrors staged content into workspace .claude/skills.
- The bridge can delete a mirrored skill directory at runtime.
- package.json has no preinstall, install, postinstall, or bin hook.
- Bridge targets require a slug and allowlist SKILL.md, schema.json, and safe template paths.
- Google OAuth storage and network calls are explicit exported integration features with HTTPS checks.
- No source evidence of stealth execution, arbitrary shell execution, or credential exfiltration.
Source & flagged code
2 flagged · loading sourcePackage metadata claims a different repository identity while copied source loads a runtime dependency bridge.
dist/discovery-D-ZJ6a6z.jsView on unpkg · L863This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/google/index.cjsView on unpkgFindings
Affected versions and remediation
This report applies to @mulmoclaude/core@1.13.0.
See all versions of @mulmoclaude/core for other recorded verdicts.
- Review the evidence and your use of @mulmoclaude/core@1.13.0 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.