afrexai-personal-finance
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing untrusted external data sources, which presents an attack surface for indirect prompt injection.
- Ingestion points: The agent is instructed to categorize daily transactions and track expenses based on bank and credit card data (SKILL.md, 'Agent Automation' section).
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to differentiate between system instructions and potentially malicious content embedded within transaction descriptions.
- Capability inventory: The skill allows the agent to write to and manage multiple sensitive files in the
finance/directory, including net worth snapshots and debt trackers (SKILL.md, 'File Structure'). - Sanitization: The skill lacks any specific guidance for the agent to sanitize, validate, or escape content from external financial records before it is incorporated into the agent's context or reported to the user.
Audit Metadata