npm security reports, with evidence.

The package has a concrete automatic postinstall chain that modifies consumer OpenCode configuration and enables an extra browser plugin. Its transparent source and lack of observed netwo...

The automatic postinstall hook broadly mutates and activates third-party AI-agent configuration, including unconditional Claude skill installation and Codex plugin activation. This meets...

The unrelated awheelmaker subscription and mailing workflow, plus the embedded mail-service credential, establishes intentional data collection and third-party outreach. The absence of an...

The package has no install hook, but runtime code deliberately extracts a wallet private key and transmits it to a remote service, including through a URL query string. That is concrete c...

This is an unconsented install-time mutation of broad AI-agent control surfaces. It meets the install-hook abuse blocking policy even without evidence of secret theft or network exfiltrat...

The package automatically mutates a foreign global AI-agent control surface and installs a skill that directs the agent to execute commands. The fixed download host and opt-out do not est...

This is an unconsented install-time remote-code execution chain: an opaque native payload is downloaded, persisted, and executed automatically. The visible source provides no integrity ve...

The package automatically writes persistent global Claude Code commands during postinstall, meeting the install-hook abuse blocking boundary. No install-time network exfiltration was obse...

This is unconsented postinstall mutation of a broad AI-agent control surface combined with remote collection of sensitive agent content. The source establishes a concrete install-time dat...

The automatic lifecycle write is not benign documentation: it plants an AI-directed instruction file in the consumer project that explicitly drives broad agent control-surface changes. Th...

This release automatically modifies foreign AI-agent configuration during npm installation and adds Windows login persistence. Those actions meet the install-hook abuse blocking policy ev...

This package performs unconsented, automatic system package installation from a registry lifecycle hook and retries it during normal startup. Its external agent-hook refresh behavior adds...

The package contains concrete AI-agent instruction injection and undisclosed host/error telemetry in its executable entrypoint. The absence of an install hook limits installation impact b...

The package contains a concrete, default-on exfiltration path for sensitive email and cloud-account metadata to a non-service endpoint. Its benign local postinstall symlink setup does not...

The automatic postinstall hook performs unconsented system-level package installation and can request elevated privileges. This is concrete install-hook abuse, not a user-invoked setup ac...

The automatic lifecycle hook modifies third-party AI-agent source and searches broadly for targets. This meets the install-hook abuse block policy despite the visible patches appearing UI...

The package has a concrete automatic postinstall chain that mutates both consumer-project and user-wide AI-agent control surfaces. This meets the install-control-surface blocking boundary...

The package combines an automatic lifecycle trigger with unconsented mutation of the consumer repository and detached process launch. Although no exfiltration was confirmed, these install...

The package has a concrete automatic postinstall path that writes and deletes under both Codex and Claude skill directories. This meets the policy for malicious install-hook abuse even wi...

The automatic postinstall hook modifies several unrelated AI-agent instruction surfaces and inserts directives for wallet and password capabilities. This is concrete AI-agent control hija...

The package has an automatic lifecycle hook that writes broad foreign AI-agent and editor configuration into the consuming project. The installed configuration adds remote MCP access and...