ledger
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- [Data Exposure & Exfiltration] (SAFE): The skill interacts with a local database via createDatabase. No network operations or access to sensitive files (e.g., credentials) were found.
- [Remote Code Execution] (SAFE): No patterns of downloading or executing remote code were detected.
- [Command Execution] (SAFE): No usage of system commands or subprocess spawning.
- [Indirect Prompt Injection] (LOW): The skill ingests data from database records and user input. Evidence: 1. Ingestion points: args in index.ts and storage.get/list results. 2. Boundary markers: Absent in generated markdown. 3. Capability inventory: Database read and data display only; no network or shell access. 4. Sanitization: Uses whitelists for categories/outcomes and parseInt for limits. The risk is low as the skill lacks exploitable capabilities.
Audit Metadata