@compr/opscontext-mcp@2.18.0
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 12d ago · by lpm-firewall-aiSource inspection found no npm install lifecycle trigger, and the reviewed configuration changes are exposed through explicit CLI setup paths. The activation request uses the package-aligned API; the reviewed evidence does not establish an attack.
Decision evidence
public snapshot- package.json defines no preinstall, install, or postinstall hook; its only lifecycle-related script is prepublishOnly.
- Agent and Claude configuration behavior is explicit setup or project-inspection functionality: skill paths are selected by scope, hook wiring uses Claude settings paths, secrets-lock reads settings, and shared-index references MCP configuration.
- The agent restart helper is conditional on daemon/build state; activation sends a request to the package-aligned api.compr.ch endpoint.
Source & flagged code
5 flagged · loading sourceSource writes installer persistence such as shell profile or service configuration.
dist/install-autostart.jsView on unpkg · L13Findings
Affected versions and remediation
This report applies to @compr/opscontext-mcp@2.18.0.
See all versions of @compr/opscontext-mcp for other recorded verdicts.
- Review the evidence and your use of @compr/opscontext-mcp@2.18.0 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.