bookkeeping
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a procedural guide for bookkeeping and does not include any executable code, network operations, or sensitive data access patterns.\n- [PROMPT_INJECTION]: The instructions focus entirely on accounting principles and do not attempt to override agent safety guidelines or behave maliciously.\n- [DATA_EXFILTRATION]: No patterns for exfiltrating data or accessing sensitive files (like credentials or system configurations) were found.\n- [REMOTE_CODE_EXECUTION]: The skill does not download or execute external code, scripts, or packages.\n- [SAFE]: While the skill ingests untrusted data such as bank-feed lines and invoices, it lacks high-risk capabilities like shell execution, network access, or file-writing that would make indirect prompt injection exploitable.
Audit Metadata