@ev-ai/agent-hook@1.2.1
Cross-runner runtime telemetry hook for Claude Code, Cursor, and Codex
AI Security Review
scanned 22d ago · by lpm-firewall-aiSource shows explicit user-command agent configuration mutation and later automatic refresh, which warrant a warning under the supplied policy. No automatic npm install mutation, credential theft, or concrete malicious chain was established.
Decision evidence
public snapshot- The explicit install command merges telemetry hooks into Claude, Cursor, and Codex configuration.
- The CLI activates configuration changes through the user-invoked install command.
- The hook builds telemetry for a configured collector; the indicated agent location identifies configuration roots.
- The launcher can start a detached refresh after an eligible session start.
- Refresh code restricts package archives to this package on registry.npmjs.org.
- package.json has no npm lifecycle scripts or runtime self-dependency.
- The indicated agent locations classify paths rather than modify configuration.
- Inspected identity code extracts account identity rather than forwarding authentication tokens.
Source & flagged code
7 flagged · loading sourceSource spawns a local helper that also contains network and dynamic execution context; review data flow before blocking.
dist/launcher.mjsView on unpkg · L2Findings
Affected versions and remediation
This report applies to @ev-ai/agent-hook@1.2.1.
See all versions of @ev-ai/agent-hook for other recorded verdicts.
- Review the evidence and your use of @ev-ai/agent-hook@1.2.1 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.