Stable terminal UI for Codex and Claude Agent SDK
LPM flags this version as an AI-agent control-surface risk. On installation, the package silently installs and synchronizes a bundled agent skill in the user-level configuration directories of both Codex and Claude. The installed skill can direct later agent activity, including launching Codex from Claude.
Package defines install-time lifecycle scripts.
package.jsonView on unpkgThe package runs an installer automatically after npm installation.
package.jsonView on unpkg · L40Source creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.
install-skills.mjsView on unpkg · L1The installer writes a bundled skill into both user-level Codex and Claude skill directories.
install-skills.mjsView on unpkg · L13Source file is highly similar to a previously finalized malicious package; route for source-aware review.
bridge/claude-agent-sdk-bridge.mjsView on unpkgSource fingerprint signature matches a known malicious package signature; route for source-aware review.
bridge/claude-agent-sdk-bridge.mjsView on unpkgPackage defines install-time lifecycle scripts.
package.jsonView on unpkg · L41The package runs an installer automatically after npm installation.
package.jsonView on unpkg · L40Source file is highly similar to a previously finalized malicious package; route for source-aware review.
bridge/claude-agent-sdk-bridge.mjsView on unpkgSource fingerprint signature matches a known malicious package signature; route for source-aware review.
bridge/claude-agent-sdk-bridge.mjsView on unpkgThe installer writes a bundled skill into both user-level Codex and Claude skill directories.
install-skills.mjsView on unpkg · L13Source creates an unconsented AI-agent control surface through install-time mutation or a default unauthenticated remote skill channel.
install-skills.mjsView on unpkg · L1