npm AI-agent policy reports, with evidence.

The source establishes automatic installation of a foreign Claude Code CLI plus persistent shell, registry, and launcher mutations. This meets the install-time foreign AI-agent control-su...

The package automatically downloads and executes an unverified native executable that installs hooks for external AI-agent tools. This satisfies the install-time AI-agent control-surface...

The automatic postinstall hook modifies broad, foreign AI-agent control surfaces. This meets the install-control-surface block policy regardless of the bundled skill's stated purpose.

The automatic postinstall hook writes and prunes user-level skill directories for both Codex and Claude. This meets the policy threshold for malicious install-hook abuse despite no confir...

The automatic post-install hook writes to global AI-agent skill locations without an explicit user command. This meets the blocking policy for unconsented install-time mutation of foreign...

The package performs unconsented postinstall mutation of foreign AI-agent configuration and changes the default Codex child-agent route. The global-install guard narrows the trigger but d...

The global-only guard limits scope, but it does not make the automatic writes to ~/.codex/config.toml and a default agent user-invoked. This is a concrete postinstall AI-agent control-sur...

The automatic postinstall hook makes broad, persistent changes to multiple global AI-agent control surfaces and the consumer project. This meets the install-hook abuse policy even though...

This is an unconsented postinstall mutation of foreign, broad AI-agent control surfaces, including recursive deletion within its installed skill directories. The bridge’s deliberate permi...

This release automatically writes and prunes user-level skills for two unrelated AI-agent platforms during postinstall, rather than requiring an explicit setup command. The added runtime...

This is an unconsented install-time mutation of global and project AI-agent control surfaces, including permissions of existing agents. The absence of exfiltration does not offset the con...

Source inspection confirms an automatic postinstall chain that mutates third-party AI client configuration and host security settings. This meets the policy threshold for malicious instal...

This package performs an unconsented postinstall mutation of a broad foreign AI-agent control surface. That behavior meets the install-control-surface blocking policy despite the absence...

The package performs unconsented postinstall mutation of foreign, user-level AI-agent control surfaces. This is concrete install-hook abuse even though no external exfiltration endpoint w...

The automatic postinstall mutates the user's global Claude Code configuration and installs a command that applies to every session. This is an unconsented broad AI-agent control-surface c...

The package performs unconsented postinstall mutation of multiple global AI-agent control surfaces. This meets the install-control-surface block policy even though no credential theft or...

The source confirms unconsented postinstall mutation of broad, foreign AI-agent configuration and hooks on global install. This meets the install-control-surface block policy despite no o...

This is unconsented postinstall mutation of a consumer AI-agent control surface, including enabled executable MCP definitions. The absence of direct exfiltration does not remove the concr...

Automatic postinstall injection into both global Codex and Claude skill directories is a concrete broad AI-agent control-surface mutation. The recursive pruning increases the persistence...

This package establishes an unconsented lifecycle-to-build chain that can overwrite generic AI-agent instructions from a remote server and self-update through npm. The behavior is a concr...

The package performs automatic postinstall mutation of broad Claude and Codex control surfaces and schedules unattended self-updates. The global-install guard reduces exposure but does no...