npm AI-agent policy reports, with evidence.

The package performs unconsented postinstall mutation of foreign AI-agent instruction files. This meets the install-control-surface blocking policy even though no exfiltration was found.

The package performs unconsented postinstall mutation of broad consumer AI-agent control files. This meets the install-control-surface blocking policy despite no observed exfiltration.

This is an unconsented postinstall mutation of broad, foreign AI-agent control surfaces. The lifecycle hook directly persists package-authored instructions into Claude Code and Codex loca...

This is an automatic postinstall mutation of foreign AI-agent control surfaces combined with execution of another CLI installer. Under the isolation policy, that concrete chain requires b...

The package implements a complete automatic lifecycle chain that patches a foreign Codex host executable and causes its own detached code to run later. This meets the install-control-surf...

The automatic postinstall hook mutates broad, user-level Claude Code and Codex instruction surfaces. This meets the install-hook policy for unconsented foreign AI-agent control-surface mu...

The package has a concrete automatic postinstall chain that writes skills into two independent agent configuration roots and installs additional dependencies. This meets the policy thresh...

This is unconsented postinstall mutation of a foreign project that plants instructions intended to cause broad AI-agent control-surface writes. The source establishes the complete install...

This is unconsented postinstall mutation of broad, foreign AI-agent control surfaces, including activation of network access and remote instruction loading. The behavior meets the install...

The automatic postinstall performs broad, persistent mutation of a consumer project's AI-agent and development control surfaces. Conditional targeting and the absence of observed exfiltra...

This is concrete automatic postinstall mutation of foreign, user-wide AI-agent configuration, which the policy requires blocking. The opt-out variable and error handling do not establish...

This is unconsented postinstall mutation of a foreign AI-agent control surface, followed by self-healing detached execution and CDP page control. That concrete lifecycle chain meets the p...

The package combines active AI-verification suppression with unneeded remote host fingerprinting and error telemetry. These are concrete runtime behaviors rather than a benign static-anal...

The automatic lifecycle hook mutates both Codex and Claude skill directories and performs user-level dependency installation. This meets the install-control-surface policy for a publish b...

This is a concrete postinstall mutation of a foreign project's AGENTS.md and agent instruction files. The guarded and non-destructive implementation does not remove the unconsented contro...

The automatic postinstall patch chain rewrites an external AI-agent package and establishes a per-user hook on future launches. This meets the install-hook abuse policy even though no sec...

The automatic lifecycle hook modifies a foreign global CodexHost launcher and renderer, then arranges later execution of package-controlled code. Explicit setup download behavior does not...

The source establishes an automatic postinstall chain that broadly modifies user AI-agent configuration and installs a separate executable MCP dependency. This meets the firewall policy f...

The automatic postinstall hook mutates numerous third-party AI-agent skill locations, including an unconditional universal fallback. This meets the blocking policy for unconsented broad A...

This is an unconsented postinstall mutation of a consumer AI-agent control surface. The automatic MCP registration and persistent agent-instruction writes meet the blocking policy.

The package has a concrete automatic postinstall chain that writes broad consumer AI-agent configuration and adds a blocking Claude hook. This meets the install-control-surface block poli...