amazon-global-selling
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional text and strategic models for market analysis, regulatory compliance, and logistics planning. No executable code, shell commands, or network exfiltration patterns were found.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided business data, which represents a potential surface for indirect prompt injection. Ingestion points: User-provided messages regarding product details and sales status (SKILL.md, 'Working Principle'). Boundary markers: Absent; there are no specific delimiters to isolate untrusted user input from the agent's core instructions. Capability inventory: Natural language analysis and planning; no tools for command execution, file system modification, or network requests are defined in the skill files. Sanitization: No specific input sanitization or filtering logic is documented in the instructions.
Audit Metadata