@highflame/overwatch@2.1.0
IDE-agnostic security daemon for AI coding assistants. Evaluates prompts, tool calls, file operations, shell commands, and MCP usage in real time for Cursor, Claude Code, GitHub Copilot, Gemini CLI, OpenAI Codex, and Kiro.
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe package’s install scripts do not include an install-time hook, and its main entry exports the module without starting the daemon. The flagged network and process activity aligns with hook evaluation, scanning, and explicitly invoked gateway setup.
Decision evidence
public snapshot- The package has no install-time lifecycle hook; its listed prepublishOnly script runs a build.
- The main entry exports OverwatchModule without starting the daemon at import time.
- The daemon sends hook events to its configured Cerberus evaluation endpoint, matching the package’s stated security-monitoring purpose.
- Gateway routing and credential selection are exposed through an explicit CLI enable command.
- The daemon makes network requests and invokes subprocesses, but the reviewed paths use them for hook evaluation and the package’s scanner.
- The daemon may transmit hook payloads to Highflame’s service; that is part of its stated function.
Source & flagged code
8 flaggedPackage source references dynamic require/import behavior.
dist/index.jsView on unpkg · L10Findings
Affected versions and remediation
This report applies to @highflame/overwatch@2.1.0.
See all versions of @highflame/overwatch for other recorded verdicts.
- Review the evidence and your use of @highflame/overwatch@2.1.0 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.