3-statements
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external financial templates and data extracted from regulatory filings, which represents a surface for indirect prompt injection.
- Ingestion points: Financial model templates provided by users and public company filings retrieved from the SEC EDGAR database.
- Boundary markers: The skill does not define specific delimiters or instructions to treat data from these external sources as potentially untrusted.
- Capability inventory: The agent is instructed to populate, fill out, and link financial models, which requires the ability to read and modify spreadsheet files or structured financial data.
- Sanitization: The reference documents focus on financial validation and mathematical integrity but do not include security sanitization for data ingested from the templates or filings.
Audit Metadata