@compr/opscontext-mcp@2.17.0
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-aiThe reviewer-directed instruction is suspicious and merits warning, but it does not prove harmful execution. The flagged persistence and agent setup are explicit-command features, while the manifest has no install lifecycle hook.
Decision evidence
public snapshot- dist/activation.js contains a reviewer-directed instruction not to re-audit it, which is manipulation evidence but does not establish an attack.
- The manifest has no preinstall, install, or postinstall hook; its only lifecycle script is prepublishOnly.
- The flagged Claude hook installer writes a hook into Claude settings when its CLI installer is invoked.
- Autostart persistence is written by an explicit CLI installer command.
- Activation sends caller-provided license and email data to the package-aligned API endpoint.
- The inspected agent integration targets concern bundled skill paths, project-file checks, or settings parsing; they do not establish unconsented broad control-surface mutation.
- The manifest's runtime dependencies do not include the package itself.
- Claude skill installation writes the package's bundled skill to the selected project or user skill directory.
- The observed activation request is tied to an explicit activation command and the package's default API host.
Source & flagged code
5 flagged · loading sourceA 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@2.17.0.
See all versions of @compr/opscontext-mcp for other recorded verdicts.
- Review the evidence and your use of @compr/opscontext-mcp@2.17.0 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.