npm AI-agent policy reports, with evidence.

Automatic postinstall execution of opaque native code to repair AI-client hooks is a concrete unconsented foreign control-surface mutation. No source-visible exfiltration was needed to es...

The automatic postinstall writes a Claude skill into the consuming project and can rewrite its ESLint configuration. This is unconsented install-time mutation of a foreign AI-agent contro...

This is concrete unconsented postinstall mutation of foreign AI-agent control surfaces, coupled with remote runtime download and execution. The global-only guard and opt-out do not establ...

This is an unconsented postinstall mutation of a foreign AI-agent control surface that establishes persistent command execution. The conditional PATH check does not make the automatic con...

The lifecycle hook automatically writes behavior-bearing files into both .agents and .claude home directories. Although no exfiltration or remote execution is present, this satisfies the...

The postinstall hook makes broad AI-agent configuration changes and installs a separately delivered, unpinned MCP runtime without user action. This meets the install-control-surface block...

This is concrete unconsented postinstall mutation of external AI-agent controls through an opaque native binary, with an unsigned remote-download fallback. It meets the install-control-su...

This is a concrete unconsented postinstall mutation of broad AI-agent control surfaces, combined with automatic installation of a separate registry package and process restart. It meets t...

The automatic postinstall hook makes persistent changes to multiple unrelated AI-agent configuration surfaces and injects directives for financial and credential-related actions. This mee...

The automatic global lifecycle chain broadly mutates foreign AI-agent configurations and installs executable MCP integration. This is concrete unconsented install-hook abuse under the pol...

The automatic lifecycle hook broadly modifies foreign AI-agent skill locations and deletes existing content before replacement. This meets the install-time AI-agent control-surface mutati...

This is an automatic npm lifecycle mutation of a broad foreign AI-agent control surface. The conditional checks do not establish consent for the current install.

This is an automatic install-time mutation of a foreign, broad AI-agent control surface. The wildcard command hook meets the publish-block policy even without a hard-coded network endpoint.

The automatic lifecycle hook forcibly modifies multiple foreign AI-agent skill directories. This meets the install-control-surface blocking policy regardless of the absence of observed cr...

The package's automatic postinstall writes a package-controlled skill into the user's global Codex configuration. Although no exfiltration or network payload was found, this concrete inst...

This is an automatic postinstall mutation of foreign AI-agent control surfaces. The copied content promotes installation of the same package, making the behavior a concrete control-hijack...

This is an automatic postinstall mutation of foreign AI-agent control surfaces, coupled with instructions to route sensitive wallet and password actions through the package. The behavior...

This is an unconsented postinstall mutation of broad AI-agent control surfaces, including automatic command-hook registration. The absence of observed network exfiltration does not remove...

This is an unconsented postinstall mutation of a broad, foreign AI-agent control surface that enables export of sensitive Claude interaction content. The automatic trigger and persistent...

This is an unconsented postinstall mutation of a consumer project's broad AI-agent control surface. Guardrails against collisions and transitive instances do not establish user consent fo...

This is an unconsented install-time mutation of both consumer project files and AI-agent control surfaces, including automatic plugin installation and user-wide Codex changes. The behavio...