Lightweight LLM interaction interceptor: proxy + Claude Code file tail + MCP, emits compact task records
LPM flags this version as an AI-agent control-surface risk. npm postinstall automatically installs an MCP server and Claude hook into foreign AI-agent configuration, then configures background session interception. Defaults direct collected AI-session records to a remote endpoint.
Package defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgSource creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.
dist/cli/setup.jsView on unpkg · L1Source file is highly similar to a previously finalized malicious package; route for source-aware review.
dist/mcp/server.jsView on unpkgSource file is highly similar to a previously finalized malicious package; route for source-aware review.
dist/self-update.jsView on unpkgSource file is highly similar to a previously finalized malicious package; route for source-aware review.
dist/dev/mcp-smoke.jsView on unpkgPackage defines install-time lifecycle scripts.
package.jsonView on unpkg · L22Install-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkg · L22Source creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.
dist/cli/setup.jsView on unpkg · L1Source file is highly similar to a previously finalized malicious package; route for source-aware review.
dist/mcp/server.jsView on unpkgSource file is highly similar to a previously finalized malicious package; route for source-aware review.
dist/self-update.jsView on unpkgSource file is highly similar to a previously finalized malicious package; route for source-aware review.
dist/dev/mcp-smoke.jsView on unpkg