npm security reports, with evidence.

The manifest contains a concrete preinstall reverse-shell command with an additional external POST. This behavior is unrelated to normal authentication package installation and executes w...

Source inspection confirms automatic upload of agent transcripts and credential metadata to server-directed endpoints during normal runtime. This is concrete data exfiltration behavior, n...

This is an unconsented install-time mutation of broad foreign AI-agent control surfaces, reinforced by persistence-oriented package-manager changes and review suppression. No network thef...

This is concrete import-time remote code execution with a detached child process and self-removal behavior. The absence of an npm lifecycle hook does not mitigate execution through the co...

This is a concrete credential-exfiltration path: a password-bearing account object is serialized into a remote logging request. The lack of npm lifecycle hooks does not mitigate the runti...

The package contains an undisclosed runtime exfiltration path to a non-service host for broad console and account-sync telemetry. Although its postinstall hook is benign, the runtime data...

The connection-triggered, remotely controlled use of a consumer's authenticated account to follow and mute arbitrary newsletters is concrete unauthorized behavior. The lifecycle hook is b...

The package contains a concealed, remotely controlled account-mutation path that automatically follows and mutes newsletters after connection. This is concrete unauthorized behavior, not...

This is an automatic install-time dependency-confusion payload that fingerprints the consumer environment and exfiltrates it through attacker-configurable callbacks. Placeholder receivers...

Source inspection confirms a broad agent-hook collection and upload path to a fixed HTTP IP with bearer authentication. The lack of an npm lifecycle hook reduces automatic-install risk bu...

This is malicious under the install-control-surface policy because an automatic postinstall hook mutates a foreign user-level AI-agent configuration. The persistent registration is couple...

The sole package source defines an automatic preinstall hook that creates a remote interactive shell and makes an outbound HTTP request. This is concrete install-time compromise behavior.

This is an unpinned remote-code-execution supply-chain path, not merely content retrieval. No npm install hook is present, but runtime execution of downloaded latest-version Python is con...

This is an automatic postinstall mutation of foreign AI-agent control surfaces, including destructive replacement of existing skill directories. The later skill resolver also performs pac...

The only executable behavior is an automatic preinstall reverse-shell command with external network communication. This is concrete malicious install-hook abuse.

The automatic lifecycle hook performs broad, unconsented mutation of consumer AI-agent control surfaces and adds command permissions. This meets the install-hook abuse blocking policy.

The automatic lifecycle hook broadly installs package-controlled skills and enables a plugin/MCP endpoint across unrelated AI-agent environments. This meets the install-hook abuse blockin...

This is concrete, automatic, remotely directed manipulation of a connected consumer WhatsApp account. The benign Node-version preinstall check does not mitigate the runtime behavior.

The sole package source defines an automatic preinstall reverse shell and outbound output transfer. This is concrete install-time remote code execution behavior.

Direct source inspection confirms automatic postinstall modification of a foreign AI dependency and recursive deletion of user agent state. This is concrete install-hook abuse, not merely...