tax-prep
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from accounting systems and CSV uploads.
- Ingestion points: Financial data from external accounting connectors and user-provided CSV files in Step 2 and Step 3.
- Boundary markers: The instructions lack explicit delimitation or instructions to treat the imported financial data as non-executable text.
- Capability inventory: The skill is configured to use environment tools for reading and fetching data.
- Sanitization: No specific sanitization or validation logic is defined for the content of the ingested files.
Audit Metadata