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.
Trigger
User runs `moryn activation apply --host codex|claude --project <path>` or uses an apply option that invokes the same activation flow.
Impact
Enables recurring package execution in the selected project's agent host after user activation.
Mechanism
Explicit project-scoped AI-agent hook configuration mutation.
Rationale
This is an explicit-user-command AI-agent configuration mutation with recurring hook execution, so it warrants a warning under the stated policy. It is not malicious because activation is not install-time or covert, and no concrete exfiltration or payload-execution chain was found.
Evidence
package.jsondist/cli.jsdist/core/host-integration-artifacts.jsdist/core/codex-activation.jsdist/core/claude-activation.jsdist/core/host-transcript-evidence.jsproject/.codex/moryn-hooks.jsonproject/.codex/hooks.jsonproject/.claude/moryn-settings.jsonproject/.claude/settings.local.jsonproject/.codex/.moryn-backups/hooks.<digest>.jsonproject/.claude/.moryn-backups/settings.local.<digest>.json