xaf-nonpersistent
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents patterns for ingesting data from external sources and user-controlled inputs, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: The
LoadDataFromApimethod (SKILL.md) and theEmailParamsnon-persistent object used inPopupWindowShowActionrepresent points where external or user-provided data enters the application flow. - Boundary markers: The provided code snippets do not include delimiters or specific instructions to the agent/application to ignore potentially malicious instructions embedded in the external data.
- Capability inventory: The skill provides templates for network communication (implied API calls) and operations like sending emails (
EmailService.Send). - Sanitization: There is no evidence of data validation, escaping, or sanitization in the provided templates for handling the external API responses or the user-provided email body.
Audit Metadata