expense-categorizer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted transaction data provided by the user.
- Ingestion point: The skill accepts bank/card statement rows as input (SKILL.md).
- Boundary markers: There are no specific delimiters or instruction-ignore warnings around the transaction data placeholder.
- Capability inventory: The skill does not include any scripts, network operations, or file system access.
- Sanitization: No sanitization or escaping of the input data is performed.
Audit Metadata