analyzing-financial-statements
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Trusted Source] (SAFE): The skill is authored by 'anthropics' and hosted in a trusted repository (anthropics/claude-cookbooks), which significantly lowers the risk profile.
- [Indirect Prompt Injection] (SAFE): The skill accepts external data formats (CSV, JSON, Excel, text) which constitutes an ingestion surface for indirect prompt injection. However, the risk is mitigated by the restricted mathematical scope of the skill. Evidence Chain: 1. Ingestion points: User-provided financial statement data as described in SKILL.md. 2. Boundary markers: Absent from documentation. 3. Capability inventory: Mathematical calculation of ratios and interpretive logic. 4. Sanitization: Not explicitly defined in documentation.
- [Data Privacy] (SAFE): No credentials, sensitive file paths, or unauthorized network communication patterns were detected in the provided skill files.
Audit Metadata