moltycash
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the
bankrCLI tool to facilitate on-chain payment operations such as tipping, hiring, and creating gigs. This involves constructing shell commands with parameters including URLs and JSON bodies. - [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection where untrusted external data is incorporated into command-line arguments.
- Ingestion points: The skill takes a username to construct a URL path and a task description for the payment metadata in the JSON-RPC body.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat these inputs as untrusted or to sanitize them before command construction.
- Capability inventory: The agent has the capability to execute shell commands using the
bankrbinary, which involves network access and financial transactions. - Sanitization: No sanitization or escaping logic is defined to handle potentially malicious characters in the username or description fields which could lead to command injection if improperly handled by the shell.
Audit Metadata