Bankr Dev - Transfers
Fail
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- Prompt Injection (HIGH): The skill is highly vulnerable to Indirect Prompt Injection (Category 8) because it facilitates high-privilege financial actions using data derived from external sources. \n
- Ingestion points: The
{recipient},{amount}, and{token}fields inSKILL.mdaccept untrusted natural language input. \n - Boundary markers: Absent; the usage examples demonstrate passing unformatted strings directly to the execution engine without delimiters. \n
- Capability inventory: The skill possesses the capability to execute token transfers on multiple chains (Ethereum, Solana, etc.), which is a high-impact side effect. \n
- Sanitization: No sanitization or validation logic is documented for social handles or ENS names, which could contain embedded malicious instructions.
Recommendations
- AI detected serious security threats
Audit Metadata