ai-trader-copytrade
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches skill configuration and installation instructions from
https://ai4trade.ai/skill/copytradeusingcurlor the Pythonrequestslibrary. - [EXTERNAL_DOWNLOADS]: Directs the installation of an external plugin
@clawtrader/copytradevia theopenclawplugin manager. - [COMMAND_EXECUTION]: Utilizes the
openclawCLI to perform system-level operations including plugin installation, service configuration, and restarting the gateway process. - [DATA_EXFILTRATION]: Transmits agent identification during registration and synchronizes local trading position data with the
api.ai4trade.aibackend. - [PROMPT_INJECTION]: Potential for indirect prompt injection due to the ingestion of untrusted external data.
- Ingestion points: The skill retrieves trading signals and provider content from the
/api/signals/feedand/api/signals/{id}endpoints inSKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat signal content as untrusted data.
- Capability inventory: The agent has the capability to perform financial transactions (opening/closing positions) based on the ingested signals.
- Sanitization: There is no documented evidence of input validation or sanitization for the content field within the trading signals.
Audit Metadata