The flagged network and process behavior belongs to the package’s CLI features: provider requests follow the selected provider, login submits credentials to the configured Symbols API, and assistant shell execution requires approval. No malicious install-time behavior was identified.
Static reason
One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source
Trigger
User invokes assistant, login, channel, or tunnel commands.
Impact
No malicious impact identified in the reviewed source.
Mechanism
The assistant routes requests to the selected AI provider; command execution requires approval. Login sends user-supplied credentials to the configured Symbols API. Tunnel creation uses the CLI authentication flow.
Evidence
~/.smblsrc~/.claude/claude_desktop_config.json~/.cursor/mcp.json~/.windsurf/mcp.json
Network endpoints5
symbols-service-production.up.railway.appapi.anthropic.comapi.openai.com