shop-amazon
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it processes untrusted data from Amazon search results and product pages.
- Ingestion points:
SKILL.md(Workflow steps 1 and 3 involves visiting external URLs). - Boundary markers: Absent; the skill does not use specific delimiters to isolate web content from agent instructions.
- Capability inventory: The agent uses browser navigation to visit and read web pages (
SKILL.md). - Sanitization: The skill implements data verification (matching ASINs and titles) but does not specifically sanitize the text for embedded instructions.
- [DATA_EXFILTRATION]: No patterns of sensitive data exposure or exfiltration were found. Network activity is limited to the well-known service Amazon.com for search and verification purposes.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns, external script downloads, or untrusted dependencies were identified.
- [COMMAND_EXECUTION]: The skill does not perform any shell command execution, privilege escalation, or persistence mechanism attempts.
Audit Metadata