portfolio-watcher-hardened
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements explicit guardrails for financial data accuracy, requiring approximate labeling and freshness notes to prevent misleading users during trading decisions.
- [SAFE]: Privacy boundaries are enforced by requiring user confirmation before displaying sensitive portfolio data in public or shared channels.
- [SAFE]: The skill requires explicit confirmation for destructive operations, such as clearing holdings or alerts, protecting against data loss from misinterpretation or prompt injection.
- [SAFE]: The safety documentation evaluates and restricts the agent's ability to execute shell commands, perform unauthorized data outflows, or access remote resources, effectively hardening the skill against common attack vectors.
Audit Metadata