wallet-compliance-scanner
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes untrusted user input which can act as an injection vector. 1. Ingestion points: User-supplied wallet addresses and token symbols defined in SKILL.md. 2. Boundary markers: No delimiters or instructions to ignore embedded content are present. 3. Capability inventory: The skill references a command-line script execution (scripts/scan_wallet.py). 4. Sanitization: No input validation or sanitization logic is provided in the available files.
- [NO_CODE] (SAFE): The functional script
scripts/scan_wallet.pymentioned in the documentation is missing from the package. - [COMMAND_EXECUTION] (SAFE): The skill describes executing a Python script with command-line arguments, but the instructions do not involve shell-specific dangerous characters, piped execution, or privilege escalation.
Audit Metadata