supply-chain-optimization-amazon-lite
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill collects natural language input from users and incorporates it into a shell command to execute a diagnostic script. \n
- Ingestion points: Business profile and supply chain data collected in SKILL.md (Steps 2 and 3). \n
- Boundary markers: The data is wrapped in a JSON string within a shell command in SKILL.md (Step 4), but no specific sanitization instructions are provided to the agent. \n
- Capability inventory: The skill executes a local Python script (scripts/calculator.py) via the command line. \n
- Sanitization: The skill relies on the agent to format user input into valid JSON for the script, which is a standard pattern but lacks explicit escaping for shell-sensitive characters. \n- [EXTERNAL_DOWNLOADS]: The generated HTML reports reference a visual chart library from a well-known CDN. \n
- Evidence: scripts/report_html.py generates HTML containing a script tag for https://cdn.jsdelivr.net/npm/chart.js. This is a standard reference to a well-known and established service.
Audit Metadata