wash-sale-detection
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses a transparent Python script (
scripts/wash_sale_scanner.py) that relies exclusively on built-in libraries likecsvanddatetime. There is no evidence of remote code execution (RCE), network requests, or unauthorized file system operations. - [SAFE]: No obfuscation techniques, such as Base64 encoding of commands, zero-width characters, or homoglyph attacks, were detected in any of the files.
- [SAFE]: The skill does not contain prompt injection attempts or instructions designed to bypass agent safety filters. The instructions are descriptive and focused on its stated purpose of tax analysis.
- [SAFE]: While the skill ingests external data (trade history in CSV format), it does not possess dangerous capabilities (like shell execution or network calls) that could be exploited via indirect prompt injection. The data is used strictly for internal calculation logic.
Audit Metadata