@compr/opscontext-mcp@2.5.3
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-aiThe package contains a real staged remote-code execution path after explicit activation, so the delivered code cannot be fully assessed from this tarball. There is no install-time execution or demonstrated malicious action in the inspected source.
Decision evidence
public snapshot- Activation accepts a server response containing a delta bundle.
- The package decrypts server-supplied module text and writes it under the user context directory.
- It dynamically imports the decrypted module, allowing server-supplied code to run.
- The manifest has no preinstall, install, or postinstall hook.
- Activation requires an explicit CLI command with a license key and email.
- Claude hook and autostart changes are separate explicit CLI commands.
- The built-in event listener binds only to the loopback address.
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@2.5.3.
See all versions of @compr/opscontext-mcp for other recorded verdicts.
- Review the evidence and your use of @compr/opscontext-mcp@2.5.3 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.