alphagbm-bps-backtest
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the official domain alphagbm.com for strategy research and developer information.
- [INDIRECT_PROMPT_INJECTION]: The skill generates natural language summaries of backtest results based on ticker inputs and historical market data.
- Ingestion points: The
tickerparameter and historical market price/volume data processed by the backend API. - Boundary markers: The skill does not explicitly define delimiters or instructions to ignore potential injections within the market data.
- Capability inventory: No dangerous capabilities such as file system writing, network exfiltration of local credentials, or shell command execution were identified in the skill's instructions.
- Sanitization: No specific sanitization or filtering logic for the summarized output is documented in the instructions.
Audit Metadata