Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.
Static reason
No blocking static signals were detected.; previous stored version diff introduced dangerous source
Trigger
User runs `lullad install claude-code --yes` or `lullad install opencode --yes`; Claude/OpenCode later activates the integration.
Impact
Changes AI-agent UI/hooks and transmits the package-owned device token to the configured Lullad API during ad delivery.
Mechanism
User-approved AI-agent hook/plugin installation with ad fetch and impression reporting.
Rationale
Source inspection confirms an explicit, persistent AI-agent advertising integration with network reporting, warranting a warning under the extension/control-surface policy. It is not malicious because no unconsented lifecycle mutation or concrete harmful chain was found.
Evidence
package.jsondist/cli.jsdist/install.jsdist/claude.jsdist/api.jsdist/store.js~/.claude/settings.json~/.claude/settings.json.lullad-backup-<timestamp>~/.config/opencode/plugins/lullad.ts~/.config/opencode/plugins/lullad.ts.lullad-backup-<timestamp>~/.lullad/config.json~/.lullad/claude-integration.json~/.lullad/claude-sessions/<sha256>.json