present
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were identified in the skill instructions.
- [COMMAND_EXECUTION]: The skill executes a local Python script (
scripts/generate_html_report.py) to transform client data into HTML reports. This is standard behavior for its stated purpose. - [DATA_EXPOSURE]: The skill accesses client-specific accounting data within the
clients/directory to generate financial statements. This data access is aligned with the skill's utility and does not target system-level or sensitive configuration files. - [PROMPT_INJECTION]: The skill processes external data sources (Trial Balances, JSON) which represents a surface for indirect prompt injection. However, the instructions emphasize producing human-readable HTML deliverables rather than model-consumed content, reducing the risk of automated injection success.
Audit Metadata