@mulmoclaude/core@0.8.2
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 ./whisper/client, ./workspace-setup/slug, ./translatio
AI Security Review
scanned 3mo ago · by lpm-firewall-aiThe package is not malicious by source evidence, but it has a concrete user-invoked agent-extension lifecycle capability that activates remote collection content. Policy classifies this as warn-level risk rather than a block because there is no lifecycle hook, stealth, or broad foreign control-surface mutation.
Decision evidence
public snapshot- Explicit registry import downloads collection bundles, then mirrors allowlisted files into `.claude/skills/<slug>`.
- `importRegistry`/`performImport` are exported runtime APIs, not lifecycle hooks.
- Imported skill content can come from configured HTTPS registries or the package's official registry.
- `package.json` has no preinstall/install/postinstall scripts or bin entrypoint.
- No credential harvesting, shell evaluation, or import-time network activity found.
- Skill writes are scoped by slug/allowlists and include path/symlink safeguards.
Source & flagged code
0 flagged · loading sourceFindings
Affected versions and remediation
This report applies to @mulmoclaude/core@0.8.2.
See all versions of @mulmoclaude/core for other recorded verdicts.
- Review the evidence and your use of @mulmoclaude/core@0.8.2 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.