market-sentinel
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements clear boundaries by explicitly stating it does not provide trading instructions, specific buy/sell points, or leverage suggestions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external tools (
tool_fetch_limit_up_stocks,tool_fetch_a_share_fund_flow, etc.). This represents a standard data ingestion surface. The skill manages this risk through a fixed output schema and lacks high-risk capabilities like file writing or code execution, minimizing the impact of potentially malicious data from those tools. - [COMMAND_EXECUTION]: The skill instructions specifically restrict tool calls to a tool runner/manifest approach and prohibit direct plugin calls or arbitrary command execution.
- [DATA_EXFILTRATION]: No evidence of unauthorized data transfer or hardcoded credentials was found. Network operations are limited to the predefined dependency tools.
Audit Metadata