financial-modeling
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes raw financial data to build forecasts and models, which is an ingestion surface for indirect prompt injection attacks.\n
- Ingestion points: External raw data used for three-statement models, DCF valuations, and scenario analyses as described in SKILL.md.\n
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to isolate the raw data from its internal modeling logic.\n
- Capability inventory: The skill utilizes the agent's ability to perform complex mathematical modeling and generate spreadsheet-style logic; no network or system-level capabilities are explicitly invoked.\n
- Sanitization: There is no mention of input validation or sanitization procedures for the data provided to the skill.
Audit Metadata