npm AI-agent policy reports, with evidence.

The automatic global lifecycle path mutates broad AI-agent configuration and enables a trusted plugin. The workspace guard does not mitigate the automatic global-install behavior.

This is a concrete automatic lifecycle chain that modifies and redirects a foreign AI-agent CLI. The observed behavior meets the install-hook abuse block boundary even without proof of se...

This is unconsented postinstall mutation of a foreign, broad AI-agent control surface. The conditional Muse check does not remove the automatic forced global installation behavior when th...

The install lifecycle automatically installs a foreign AI-agent CLI and persists broad user-environment changes. This is concrete unconsented install-hook abuse under the stated policy.

The concrete postinstall behavior mutates a foreign, home-directory AI-agent skill surface automatically. The lack of network or secret theft does not neutralize that control-surface take...

The package performs an unconsented postinstall write to a broad AI-agent control surface in the consumer project. Although no exfiltration or network activity was found, this concrete li...

This is concrete install-time mutation of foreign and broad AI-agent control surfaces, including automatic pre-message behavior. It meets the policy threshold for malicious install-hook a...

The automatic postinstall performs broad mutation of foreign AI-agent configuration and instruction files, plus package-manager installs. This is a concrete unconsented agent-control hija...

The automatic lifecycle hook modifies multiple external AI-agent skill directories, including fallback targets, rather than limiting setup to an explicit user command or package-owned loc...

The package performs an unconsented global-install lifecycle mutation of multiple foreign AI-agent control surfaces, then injects content into their sessions. No network theft was found,...

The automatic lifecycle hook mutates a global AI-agent skill directory and can recursively delete a pre-existing matching entry. The weak installation guard makes this occur beyond an exp...

The automatic global postinstall mutates a shared AI-agent skill control surface and can recursively remove existing matching content before replacing it. This is concrete install-hook ab...

The install-time overwrite of a foreign global AI-agent instruction file is concrete unconsented control-surface mutation. No exfiltration was found, but the lifecycle behavior meets the...

The automatic lifecycle hook force-installs a package-controlled skill into user-wide directories for two agent ecosystems. That meets the install-control-surface block policy regardless...

The postinstall hook concretely mutates consumer .claude and .github agent-control directories without an explicit user command. That meets the install-time AI-agent control-surface abuse...

The postinstall hook writes executable-behavior instructions into a foreign user-level AI-agent configuration without an explicit user command. That meets the install-control-surface bloc...

The automatic postinstall hook writes AI-agent command files into the consumer project and supplies commands that direct later tool use and file mutation. This meets the install-hook abus...

The automatic global lifecycle hook modifies several unrelated AI-agent instruction surfaces and installs a remote-instruction requirement. The explicit update command's registry traffic...

This is an unconsented install-time mutation of broad foreign AI-agent control surfaces, amplified by a mandatory remote instruction fetch. The behavior is concrete and reachable from the...

The automatic postinstall chain writes a bundled capability into global locations for many foreign AI agents. Collision safeguards do not provide user consent for this broad control-surfa...

This is an unconsented postinstall mutation of a broad foreign AI-agent control surface. The guarded implementation does not remove the automatic, cross-agent configuration change.