amz-account-health-triage
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, command execution, or sensitive data access were detected. The skill provides a logic-based framework for prioritizing Amazon account violations based on user-supplied text or screenshots.
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface for untrusted content.
- Ingestion points: Amazon Account Health Rating (AHR) snapshots or text dumps provided by the user (found in
SKILL.md). - Boundary markers: No specific delimiters or instructions to ignore embedded content are defined.
- Capability inventory: The skill utilizes no tools and has no filesystem or network capabilities.
- Sanitization: No sanitization is applied to the input data.
- Note: Because the skill lacks executable capabilities, the risk associated with processing untrusted data is negligible.
- [EXTERNAL_DOWNLOADS]: The skill includes a link to a WhatsApp group (chat.whatsapp.com) for author updates. This is a promotional link to a well-known service and does not trigger automated code execution or data exfiltration.
Audit Metadata