@compr/opscontext-mcp@2.10.0
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 reviewed source exposes agent integration and autostart through explicit user commands, with no npm install lifecycle hook that activates them. The inspected network use is license activation to the package-associated API, and no concrete attack behavior was found.
Decision evidence
public snapshot- The manifest defines a prepublishOnly script but no preinstall, install, or postinstall hook.
- Claude hook installation is reached through an explicit CLI command and adds package hook entries to Claude settings.
- The hook installer writes local hook scripts and appends settings entries; the shipped code does not show installation being triggered automatically by npm.
- Skill installation is scoped to the project or user Claude skill directory and avoids overwriting an existing skill unless forced.
- Autostart setup writes a launch agent only when its installer command is invoked; shared-index behavior requires an environment opt-in.
- License activation posts license data to the package's configured activation API; no unrelated credential forwarding or attack behavior was identified.
Source & flagged code
7 flagged · loading sourcePackage source references dynamic require/import behavior.
dist/adapters.jsView on unpkg · L47A 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@2.10.0.
See all versions of @compr/opscontext-mcp for other recorded verdicts.
- Review the evidence and your use of @compr/opscontext-mcp@2.10.0 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.