@compr/opscontext-mcp@2.4.0
OpsContext for AI Agents — read-only fleet visibility (PM2/nginx/Docker/git/cron) + tamper-evident audit log + policy-as-code hooks. The ops + compliance layer Claude Code can't grow natively.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiNo malicious install-time or covert exfiltration chain is present, but the explicit activation path is a remote code delivery mechanism whose payload is absent from the tarball and not independently authenticated in the inspected source.
Decision evidence
public snapshot- Activation fetches an encrypted remote delta from api.compr.ch.
- The delta is decrypted, written as .mjs files, then dynamically imported.
- Claude hook and LaunchAgent installers can persist behavior, but only through explicit CLI commands.
- package.json has no preinstall, install, or postinstall hook.
- The hook posts to a loopback endpoint, not an external collector.
- No shipped source shows credential harvesting or external data exfiltration.
Source & flagged code
7 flagged · loading sourcePackage source references dynamic require/import behavior.
dist/adapters.jsView on unpkg · L46A manifest entrypoint or package-local install chain reaches persistence behavior.
dist/install-autostart.jsView on unpkg · L13Findings
Affected versions and remediation
This report applies to @compr/opscontext-mcp@2.4.0.
See all versions of @compr/opscontext-mcp for other recorded verdicts.
- Review the evidence and your use of @compr/opscontext-mcp@2.4.0 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.