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 mcpbox-claude codex-init, cursor-init, or kimi-init.
Impact
Future agent sessions may load policy/hooks and connect to the configured MCP endpoint.
Mechanism
Explicit agent configuration and hook installation
Rationale
Source confirms explicit user-command mutation of AI-agent control surfaces, including global Codex/Kimi configuration. This warrants a warning under the lifecycle policy, not a publish block.
Evidence
bin/mcpbox-claude.mjslib/policy.mjslib/codex.mjslib/cursor.mjslib/kimi.mjshooks/session-start.mjsAGENTS.mdCLAUDE.md.cursor/rules/mcpbox-policy.mdc.cursor/mcp.json~/.codex/config.toml~/.kimi-code/mcp.json~/.kimi-code/config.toml~/.kimi-code/mcpbox/