ScopeBlind Passport
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is a coherent access-control and audit wrapper, but installing it means trusting external npm tools to mediate MCP calls and keep local receipts and signing keys.
Install this only if you want an external npm-based gateway to wrap your MCP servers. Pin or verify the npm packages, protect the generated keys and receipts, prefer one-time approvals, and enable --enforce if you expect policies to block actions rather than only log them.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
You would be trusting the current npm versions of these packages to act as a security gateway for MCP tool calls.
The skill depends on globally installed, unpinned npm packages. This is central to the stated purpose, but the exact code installed can change over time.
npm install -g protect-mcp@latest @scopeblind/passport@latest
Verify the npm/GitHub provenance before installing, and consider pinning exact package versions instead of using @latest.
If you approve an always-allow request, a previously blocked tool could be usable for the rest of the session rather than just for one action.
The documented approval flow lets the agent call a localhost approval API after user approval, including a broader 24-hour always-allow option.
For always-allow this tool (session-scoped, 24h TTL): curl -s -X POST http://127.0.0.1:9876/approve ... "mode":"always"
Use one-time approvals for specific requests unless you intentionally want a 24-hour session approval for that tool.
Receipts and digests may reveal what tools the agent used and when, and possibly sensitive workflow metadata depending on the underlying tool calls.
The skill intentionally creates persistent local records of agent activity for auditing.
Shadow mode — logs every tool call with a signed receipt ... Local daily digest — human-readable summary of what your agent did
Store generated keys, receipts, and digest files in a protected project directory and avoid sharing receipts unless you understand what they contain.