npm AI-agent policy reports, with evidence.

This is a concrete unconsented postinstall mutation of a foreign AI-agent control surface, which meets the blocking policy. Checksums mitigate the binary-download risk but do not remove t...

The bundled source confirms an unconsented postinstall mutation of foreign and broad AI-agent control surfaces. Benign-looking rule content does not remove this install-time control-surfa...

The package executes automatically on install and writes persistent controls for several foreign AI-agent integrations in the consuming repository. The self-exclusion from review reinforc...

This is concrete, unconsented postinstall mutation of foreign/broad AI-agent control surfaces, compounded by package-manager configuration changes. The absence of network exfiltration doe...

The package has a concrete install-time chain that modifies multiple consuming-project AI-agent instruction and extension locations, rather than requiring an explicit setup command. That...

The behavior is explicit in source and occurs automatically during dependency installation, meeting the firewall block policy for foreign/broad AI-agent control-surface mutation.

This is an unconsented postinstall mutation of foreign, broad AI-agent control surfaces, reinforced by persistent package-manager configuration changes. Lack of exfiltration does not remo...

This is an unconsented postinstall mutation of foreign, broad AI-agent control surfaces, not merely a user-invoked setup command. The absence of exfiltration does not remove the concrete...

This is concrete unconsented postinstall mutation of foreign AI-agent control surfaces, meeting the blocking policy. Global-install gating and opt-outs reduce reach but do not establish c...

This is an unconsented npm postinstall mutation of foreign, broad AI-agent control surfaces, meeting the blocking policy. The remote executable download further expands the install-time e...

This is an unconsented npm postinstall mutation of multiple foreign AI-agent control surfaces, compounded by remote native payload execution. The global-install guard and opt-outs do not...

This is a concrete install-time mutation of foreign AI-agent control surfaces, compounded by unverified remote native payload execution. The global-install guard does not make the behavio...

This is concrete unconsented postinstall mutation of foreign and broad AI-agent control surfaces, meeting the blocking policy. No exfiltration is needed for this lifecycle hijack to be ha...

This is concrete unconsented postinstall mutation of broad, foreign AI-agent control surfaces. The absence of confirmed exfiltration does not mitigate the install-time control-surface hij...

The install hook performs the exact broad AI-agent control-surface mutation reserved for blocking. Lack of observed exfiltration does not mitigate the unconsented persistence and behavior...

This is concrete install-time mutation of broad, foreign AI-agent control surfaces without an explicit user command. The lack of detected exfiltration does not remove the persistence and...

This is a concrete unconsented postinstall mutation of foreign, broad AI-agent control surfaces, meeting the blocking policy. No external exfiltration was needed to establish the harmful...

The install hook performs unconsented mutation of foreign, broad AI-agent control surfaces and approval settings. This meets the blocking policy even though no network exfiltration was fo...

Source inspection confirms the policy-defined blocking chain: automatic postinstall mutation of third-party AI-agent configuration, coupled with unverified native payload installation and...

This is a concrete unconsented postinstall mutation of foreign AI-agent control surfaces. The package’s permission hardening does not remove the lifecycle-based global control-surface write.

The global-install lifecycle path is a concrete unconsented postinstall mutation of broad foreign AI-agent control surfaces. Guardrails and lack of observed network activity do not remove...