supply-chain-optimization-walmart
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data—such as product names, cost descriptions, and bottleneck details—and interpolates this content directly into generated HTML and Markdown reports.
- Ingestion points: Data enters via the
SupplyChainInputclass inscripts/calculator.pyand is processed byscripts/report_doc.pyandscripts/report_html.py. - Boundary markers: No specific boundary markers or instructions to ignore embedded malicious strings are present in the skill's logic.
- Capability inventory: The skill utilizes file-writing capabilities (
open().write()) to createreport.mdandreport.htmlbased on input data. - Sanitization: The Python scripts do not perform HTML escaping or input validation on the strings before writing them to the file system. If a user provides malicious scripts or markdown-breaking content, it could be executed or rendered when the resulting reports are opened.
Audit Metadata