analyzing-financial-statements
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted financial statement data in various formats including CSV, JSON, and Excel files, which represents an indirect prompt injection surface.
- Ingestion points: The skill ingests data from external files (CSV, JSON, Excel) and text descriptions provided by the user.
- Boundary markers: There are no defined delimiters or instructions to the agent to disregard natural language instructions that might be embedded within the structured data fields.
- Capability inventory: The skill performs calculations and generates analytical interpretations, which can be influenced by malicious data.
- Sanitization: No evidence of sanitization, schema validation, or content filtering is provided in the skill documentation to mitigate data-driven attacks.
Audit Metadata