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 `stars install-skill` and confirms skill or MCP setup.
Impact
Can add a configured MCP server, including broad tool approval in Codex configuration, and store a supplied token for the selected Starlens endpoint.
Mechanism
Interactive AI-agent skill and MCP configuration writer.
Rationale
Source inspection found no concrete malicious chain, but the explicit installer mutates broad AI-agent control surfaces and configures an enabled MCP server with permissive Codex tool approval. Per policy, this warrants a warning rather than a block.
Evidence
package.jsonsrc/index.mjssrc/api.mjssrc/token.mjssrc/install-skill/index.mjssrc/install-skill/mcp-config.mjs~/.codex/config.toml~/.cursor/mcp.json~/.config/opencode/opencode.json~/.starlens/agent.env