bezalel-cards
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests transaction data and merchant information through the
cards__list_transactionstool. This creates a surface where an external attacker (e.g., a malicious merchant) could attempt to influence the agent's behavior by embedding instructions in transaction memos or merchant names. - Ingestion points: Transaction details and merchant metadata retrieved via
cards__list_transactionsinSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the data returned by the transaction list tool.
- Capability inventory: The skill possesses the capability to create, pause, and close financial instruments, and reveals sensitive PII/PCI data (Full PAN, CVV, Expiry).
- Sanitization: There is no evidence of sanitization or filtering for merchant-provided strings before they are processed by the agent.
Audit Metadata