npm detections from LPM Firewall.

Inspected source establishes unconsented postinstall mutation of OpenCode's user-wide agent control surface. This meets the blocking policy independently of scanner similarity labels or c...

Source proves unconsented postinstall mutation of foreign global AI-agent instruction surfaces, meeting the blocking policy. Package-specific naming, collision checks, and an opt-out do n...

Inspected source proves unconsented postinstall mutation of broad foreign AI-agent control surfaces. This meets the blocking policy independently of scanner labels or unproven credential-...

Inspected source establishes automatic, unconsented mutation of a broad AI-agent control surface, which meets the blocking policy. The NextSpark guard does not restrict writes to verified...

Source establishes unconsented install-time replacement of a foreign agent control surface, including deletion of existing rules and skills. This meets the blocking policy even without cr...

Source confirms automatic, obscured transmission of host information unrelated to the stylesheet functionality. This supports blocking for malicious install-hook abuse, without claiming t...

Inspected source proves automatic, unconsented mutation of two foreign global AI-agent control surfaces. The blocking decision rests on that lifecycle behavior, independently of scanner s...

Source proves unconsented postinstall mutation of foreign, global AI-agent control surfaces, meeting the supplied blocking policy. Package ownership of the registered server and preservat...

The inspected lifecycle chain performs automatic, unconsented writes to multiple foreign AI-agent skill directories. This meets the blocking policy for agent control-surface mutation rega...

Inspected source establishes unconsented postinstall mutation of multiple foreign AI-agent control surfaces. This meets the blocking policy even though the installed instructions align wi...

Inspected source establishes unconsented postinstall mutation of multiple foreign AI-agent control surfaces. This meets the supplied blocking policy even though the skill serves package-r...

Source confirms unconsented npm postinstall mutation of multiple foreign AI-agent control surfaces. This meets the explicit blocking policy even though the installed delegation functional...

The inspected lifecycle chain performs unconsented writes to foreign agents' global instructions. This meets the explicit blocking rule for installation-time AI-agent control-surface muta...

Inspected source establishes unconsented postinstall mutation of foreign and shared AI-agent control surfaces, which meets the blocking policy. Blocking rests on the automatic instruction...

Source establishes unconsented postinstall mutation of foreign, global AI-agent control surfaces. This meets the blocking policy regardless of the delegation feature's package alignment.

Source establishes unconsented postinstall mutation of a shared Pi agent instruction file, including a user-directory fallback. This meets the blocking rule for foreign or broad AI-agent...

The source establishes an unconsented postinstall mutation of a shared AI-agent control surface, including a user-wide fallback. Under the supplied policy, this warrants blocking despite...

Source establishes an unconsented postinstall write to a shared AI-agent instruction file, including a user-wide fallback. This meets the blocking control-surface policy despite the task-...

The inspected lifecycle chain performs unconsented mutation of OpenCode's global control surface and removes unrelated global MCP packages. This independently supports blocking, regardles...

Source proves unconsented postinstall replacement of a foreign AI-agent client and mutation of its updater configuration. This meets the blocking rule for agent control hijacking despite...

Inspected source establishes an automatic postinstall chain that mutates foreign, user-wide AI-agent configurations and instructions without consent. This meets the explicit blocking poli...