financial-statement-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of financial statements provided by the user.
- Ingestion points: The skill accepts PDFs, screenshots, and tabular data (balance sheets, income statements, cash-flow statements) as described in the workflow.
- Boundary markers: No explicit boundary markers or instructions to ignore instructions embedded within the user-provided documents are present.
- Capability inventory: The skill has the capability to generate external files using document creation tools.
- Sanitization: There is no evidence of sanitization or filtering of the content extracted from the financial statements before it is processed or used in document generation.
Audit Metadata