risk-adjusted-return-optimizer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): No instructions attempting to bypass safety protocols or override system prompts were identified. The workflow is purely instructional for investment analysis.- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or network exfiltration patterns are present. The reference to 'findata-toolkit-cn' is for external data retrieval and does not involve credential handling.- [Unverifiable Dependencies] (SAFE): The skill does not perform any package installations or remote script executions.- [Indirect Prompt Injection] (INFO): The skill ingests user input (risk preferences, budget) and external market data from a toolkit. While this creates an ingestion surface for untrusted data, the skill is limited to generating formatted investment reports (display only) and lacks high-privilege write or execute capabilities.- [Obfuscation] (SAFE): All content is provided in cleartext Markdown; no encoding or hidden characters were found.
Audit Metadata