npm AI-agent policy reports, with evidence.

Source proves unconsented postinstall mutation of a broad, foreign AI-agent control surface, which meets the explicit blocking policy. The finding does not depend on citation limits or in...

The automatic postinstall writes a foreign agent's plugin-loading control surface without explicit setup consent, meeting the supplied blocking policy. Patch validation and package-owned...

Source establishes unconsented postinstall mutation of a foreign AI-agent control surface, meeting the specified blocking policy. The interactive consent path does not protect noninteract...

The inspected lifecycle path automatically writes foreign global AI-agent control surfaces, including Gemini's instruction file, without consent. This meets the blocking rule despite the...

The inspected lifecycle performs unconsented mutation of a foreign, global AI-agent control surface, which meets the supplied blocking rule. Existing Telora binaries and a separate intera...

The inspected lifecycle chain performs unconsented global AI-agent instruction and permission mutation, meeting the supplied blocking policy. The local-install guard and backups do not re...

Source establishes unconsented postinstall mutation of a broad AI-agent instruction surface. This meets the supplied blocking policy even without evidence of credential theft or remote pa...

The source proves unconsented npm postinstall mutation of foreign, global AI-agent control surfaces, which meets the supplied blocking rule. This decision rests on the active installation...

The source establishes unconsented install-time mutation of broad AI-agent control surfaces, including deletion of unrelated global hooks. This meets the blocking policy independently of...

The inspected chain establishes unconsented postinstall mutation of a foreign, user-wide AI-agent control surface, which meets the supplied blocking policy. The visible statusline purpose...

Source proves unconsented postinstall mutation of a broad AI-agent control surface, enabling detailed telemetry by default. This meets the blocking policy independently of whether telemet...

Source proves unconsented postinstall mutation of a broad AI-agent control surface. The supplied policy requires blocking this behavior even though the bundled instructions appear ordinary.

The inspected lifecycle performs unconsented writes to Claude's global command surface, including unconditional replacement of existing commands. This meets the supplied blocking rule for...

The inspected lifecycle chain performs an unconsented install-time mutation of a foreign AI-agent control surface, meeting the blocking policy. The local destination and overwrite guard l...

Source proves unconsented postinstall mutation of a broad AI-agent control surface, which meets the blocking policy. The block rests on the global configuration change, without assuming t...

The inspected global postinstall path performs unconsented mutation of foreign AI-agent configuration and broad instruction files, meeting the blocking policy. The local-install guard and...

The inspected source establishes unconsented postinstall mutation of two foreign, global AI-agent control surfaces. This meets the supplied blocking policy even though the registered MCP...

Source establishes an automatic, unconsented postinstall mutation of a broad foreign AI-agent control surface. This meets the supplied blocking policy even though the writer preserves exi...

Source confirms unconsented postinstall mutation of a broad AI-agent control surface, which meets the blocking policy. The package-aligned destination does not excuse globally enabling co...

The inspected lifecycle chain performs unconsented writes to global Gemini instructions and Claude configuration, meeting the supplied blocking rule for foreign AI-agent control surfaces....

Source establishes unconsented postinstall mutation of broad foreign AI-agent control surfaces, meeting the supplied blocking policy. Package-aligned functionality and partial configurati...