@compr/opscontext-mcp@2.19.1
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 6d ago · by lpm-firewall-aiThe package has no install lifecycle trigger, but init defaults to installing a post-commit hook in noninteractive use. Because that hook pushes commits to configured remotes without per-commit confirmation, this presents a concrete residual risk and warrants a warning.
Decision evidence
public snapshot- package.json has no install-time lifecycle hook; its prepublishOnly script is release work.
- The init command is an explicit CLI action, and noninteractive mode automatically answers yes to setup prompts.
- The post-commit prompt labels the hook as auto-push and allows an interactive user to decline; otherwise init writes .git/hooks/post-commit.
- The generated hook asynchronously pushes the current branch to the configured origin and gdrive remotes after commits.
Source & flagged code
7 flagged · loading sourceThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/install-autostart.jsView on unpkgSource 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@2.19.1.
See all versions of @compr/opscontext-mcp for other recorded verdicts.
- Review the evidence and your use of @compr/opscontext-mcp@2.19.1 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.