npm AI-agent policy reports, with evidence.

The automatic lifecycle chain silently mutates global instruction surfaces for multiple AI-agent products. This meets the install-control-surface blocking policy regardless of the absence...

The package has a concrete automatic postinstall path that installs code into a global agent extension location and alters future agent sessions. No self-dependency or network theft was f...

The automatic postinstall writes and activates code in Pi's user-wide extension location, then alters agent context and prompts. This meets the install-control-surface block policy despit...

This is an unconsented postinstall mutation of a foreign, user-wide AI-agent control surface. Integrity checks on the downloaded binary do not mitigate the automatic Cursor configuration...

The package has a concrete automatic postinstall chain that modifies consumer OpenCode configuration and enables an extra browser plugin. Its transparent source and lack of observed netwo...

The automatic postinstall hook broadly mutates and activates third-party AI-agent configuration, including unconditional Claude skill installation and Codex plugin activation. This meets...

This is an unconsented install-time mutation of broad AI-agent control surfaces. It meets the install-hook abuse blocking policy even without evidence of secret theft or network exfiltrat...

The package automatically mutates a foreign global AI-agent control surface and installs a skill that directs the agent to execute commands. The fixed download host and opt-out do not est...

The package automatically writes persistent global Claude Code commands during postinstall, meeting the install-hook abuse blocking boundary. No install-time network exfiltration was obse...

This is unconsented postinstall mutation of a broad AI-agent control surface combined with remote collection of sensitive agent content. The source establishes a concrete install-time dat...

The automatic lifecycle write is not benign documentation: it plants an AI-directed instruction file in the consumer project that explicitly drives broad agent control-surface changes. Th...

The package contains concrete AI-agent instruction injection and undisclosed host/error telemetry in its executable entrypoint. The absence of an install hook limits installation impact b...

The package has a concrete automatic postinstall chain that mutates both consumer-project and user-wide AI-agent control surfaces. This meets the install-control-surface blocking boundary...

The package has a concrete automatic postinstall path that writes and deletes under both Codex and Claude skill directories. This meets the policy for malicious install-hook abuse even wi...

The automatic postinstall hook modifies several unrelated AI-agent instruction surfaces and inserts directives for wallet and password capabilities. This is concrete AI-agent control hija...

The package has an automatic lifecycle hook that writes broad foreign AI-agent and editor configuration into the consuming project. The installed configuration adds remote MCP access and...

The package has a concrete automatic lifecycle chain that broadly mutates foreign AI-agent control surfaces and the user environment. This meets the install-hook abuse blocking policy reg...

The automatic postinstall hook changes a foreign shared AI-agent configuration by installing bundled agents and commands. That meets the blocking policy even though the source does not sh...

The automatic postinstall performs unconsented, broad mutation of consumer AI-agent configuration and installs executable control hooks. This meets the blocking policy even though the ins...

This is concrete unconsented postinstall mutation of foreign, broad AI-agent control surfaces. The installed capability also drives automated access-evasion behavior, so it meets the inst...

The package uses an automatic postinstall to mutate consumer project agent configuration and persist its own future execution in the consumer package.json. This meets the install-hook abu...