@ev-ai/agent-hook@1.0.9
Cross-runner runtime telemetry hook for Claude Code, Cursor, and Codex
AI Security Review
scanned 22d ago · by lpm-firewall-aiThe inspected source implements explicit user-command agent configuration mutation and telemetry delivery, which the supplied policy classifies as a warning. No npm lifecycle mutation or concrete malicious chain supports blocking publication.
Decision evidence
public snapshot- package.json exposes a CLI and declares no npm lifecycle hooks or runtime self-dependency.
- The explicit install command invokes agent hook configuration setup.
- Setup writes command hooks into project Cursor and Codex configurations and also supports Claude.
- dist/hook.mjs posts telemetry to the configured collector.
- Configuration changes require an explicit CLI command; no automatic npm install mutation was found.
- The indicated agent integration locations identify configuration roots rather than writing them.
- No concrete malicious attack was established from the inspected behavior.
Source & flagged code
5 flagged · loading sourceA single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/hook.mjsView on unpkg · L4Source combines command execution, command-output handling, and outbound requests; review data flow before blocking.
dist/hook.mjsView on unpkg · L3Findings
Affected versions and remediation
This report applies to @ev-ai/agent-hook@1.0.9.
See all versions of @ev-ai/agent-hook for other recorded verdicts.
- Review the evidence and your use of @ev-ai/agent-hook@1.0.9 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.