financial-modeling
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes established financial frameworks and templates from trusted sources such as David Skok, Ben Murray, and Meritech Capital.
- [SAFE]: The shipped script
scripts/check-output.pyis a benign utility for validating deliverable quality by checking for the presence of specific keywords. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided financial data to generate reports, creating a surface for indirect instructions. Ingestion points: User-supplied business metrics and revenue inputs defined in Phase 1 and 2 of
SKILL.md. Boundary markers: Absent; the skill lacks explicit instructions to ignore embedded instructions in data. Capability inventory: The skill uses file-writing for templates and executes a local validation script (scripts/check-output.py). Sanitization: Absent; no specific validation or filtering of user data is implemented. The risk is considered minimal and inherent to the skill's analytical purpose.
Audit Metadata