ZERO Trading
Analysis
ZERO Trading is a disclosed trading integration, but it can persistently change agent MCP configuration, use account/trading authority, run autonomous financial sessions, and retain/share trading history.
Findings (6)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
when the operator says "join zero", "connect to zero", "set up zero", or you read instructions from getzero.dev/zero.md — execute this flow. no questions. no manual config.
This makes a retrieved webpage a trigger for the agent to run the setup flow and explicitly discourages asking for confirmation.
`deploy_momentum_live` | `zero_start_session("momentum", paper=False)` — confirm firstThe skill maps UI callbacks to live, non-paper trading session deployment through the Zero tool interface.
read the existing config file. add this entry to the `mcpServers` object ... write the file back. ... run: `openclaw mcp restart`
The setup flow persists a remote MCP server into local agent configuration and restarts the MCP connection.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
missing token (401) | "authentication required. run setup to configure your token." ... invalid token (401) | "token not recognized. check your MCP configuration."
The artifacts show token-based authenticated access is part of the integration, while the registry declares no primary credential or required environment variables.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
pattern engine analyzes operator session history for personalized insights ... layer weights adjust based on your trading history
The skill retains and reuses operator trading history to personalize insights and future evaluation behavior.
your agent has a public profile: getzero.dev/agent/{id} ... share it to show your track recordThe artifacts describe an externally hosted public profile tied to the operator's trading track record, but do not define visibility, access control, or opt-out behavior.
