bambu-filament-tracker
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Gmail message bodies and subjects to extract purchase information.
- Ingestion points: External email content from Bambu Lab and Amazon orders is retrieved via the
gwstool inscripts/tracker.dart. - Boundary markers: The output is structured as a Markdown table but lacks explicit delimiters or instructions to ignore embedded commands within the extracted text.
- Capability inventory: The script's capabilities are limited to reading data via
gwsand printing to standard output. It does not perform network requests or write to the file system. - Sanitization: The script cleans the input by removing zero-width characters (
\u200b) which can be used to hide malicious content. - [COMMAND_EXECUTION]: The script executes the
gwscommand-line utility. It uses a structured argument list and JSON encoding for parameters, which prevents traditional shell command injection.
Audit Metadata