customer-health-check
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied customer data which introduces a potential attack surface for indirect prompt injection.\n
- Ingestion points: The prompt template in
SKILL.mdasks the user to paste customer data (e.g., name, activity, spend) into the prompt context.\n - Boundary markers: There are no delimiters or instructions to ignore potential commands embedded within the pasted data.\n
- Capability inventory: The skill contains no code or scripts and does not request any specific tool permissions.\n
- Sanitization: No sanitization or validation is applied to the data provided by the user.
Audit Metadata