npm AI-agent policy reports, with evidence.

The automatic lifecycle hook writes package-authored agent definitions into a consumer or home AI-agent directory. This meets the blocking policy for unconsented postinstall mutation of a...

The package automatically provisions and mutates AI-agent control surfaces in the consuming project and user environment. Its self-dependency range increases lifecycle-chain risk, so this...

This package performs automatic postinstall repair of broad Claude lifecycle hooks rather than limiting agent configuration to an explicit user command. That matches install-hook abuse ev...

This is an unconsented install-time mutation of a consumer project's persistent execution and AI-agent control surfaces. The detached reapplication makes the mutation survive the package...

The automatic lifecycle hook performs broad consumer-project and user-wide AI-agent configuration mutations. This meets the blocking policy for unconsented postinstall mutation of foreign...

The automatic lifecycle hook rewrites consumer AI configuration and routes AI calls through code that transmits prompt and response data. This is a concrete unconsented AI-agent control h...

The package has a concrete automatic install-time chain that broadly mutates foreign AI-agent control surfaces. This meets the install-hook abuse blocking boundary even though no credenti...

The package performs broad, automatic AI-agent and project mutation during postinstall, rather than requiring an explicit user command. Its detached reconciliation mechanism makes those c...

This is an unconsented postinstall mutation of broad, foreign AI-agent control surfaces. The lack of network access in the installer does not remove the persistence and control-surface risk.

This is an unconsented postinstall mutation of broad AI-agent control surfaces, including persistent instructions and command hooks. The automatic lifecycle chain meets the publish-block...

This is an automatic install-time mutation of foreign AI-agent control surfaces across multiple products. Although scoped to global installs and using a loopback endpoint, it materially c...

The automatic postinstall hook mutates a broad set of foreign AI-agent control surfaces, meeting the install-control-surface block policy. No runtime self-dependency or install-time netwo...

The package performs unconsented postinstall mutation of both consumer project and AI-agent control surfaces, including third-party Claude plugins and user-wide Codex registrations. This...

The automatic lifecycle chain mutates a foreign AI host and installs a detached self-healing mechanism. This is concrete install-hook abuse even though no credential theft was found.

The package automatically modifies consumer lifecycle configuration and installs AI-agent plugins during postinstall. This is concrete install-hook abuse rather than an explicit user-invo...

The package combines an automatic install hook, non-interactive consumer-project mutation, and unrequested installation of third-party AI-agent plugins. This is a concrete unconsented lif...

The package has a postinstall hook that automatically changes both Codex and Claude skill directories and installs user-environment dependencies. This is concrete install-hook abuse under...

The package performs unconsented postinstall mutation of a foreign, broad AI-agent skill directory. Its automatic remote archive download and extraction increases the install-time supply-...

The automatic lifecycle hook modifies foreign global AI-agent configuration surfaces and performs further user-environment dependency installation. This meets the install-control-surface...

This is an unconsented postinstall mutation of a foreign AI-agent control surface that weakens both sandboxing and authentication. The lack of observed exfiltration does not neutralize th...

The automatic postinstall fan-out mutates broad third-party AI-agent control surfaces, meeting the install-control-surface blocking policy. No exfiltration was found, but it is not needed...