analyzing-financial-statements
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (LOW): The skill is susceptible to Indirect Prompt Injection due to its data processing nature.
- Ingestion points: The skill explicitly accepts and processes external data from CSV, JSON, text descriptions, and Excel files (mentioned in Input Format).
- Boundary markers: Absent. The instructions do not define delimiters or provide clear 'ignore instructions' warnings to the agent regarding the content of these files.
- Capability inventory: The skill references internal scripts (
calculate_ratios.py,interpret_ratios.py) to perform calculations and generate formatted reports, which could be influenced by malicious data inputs. - Sanitization: None detected. There are no mechanisms described for sanitizing or validating the content of external financial documents before they are processed by the agent.
Audit Metadata