disposable-email-address
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a mechanism to read emails from external senders, which creates a surface for indirect prompt injection attacks.
- Ingestion points: The
checkaction inSKILL.mdandschema.mdretrieves thebody,subject, andfromfields of emails received at the disposable address. - Boundary markers: The instructions do not specify any delimiters or warnings to the agent to ignore instructions embedded within the email content.
- Capability inventory: The skill allows fetching full message content and listing active addresses.
- Sanitization: No sanitization or filtering of the retrieved email body is mentioned or required by the schema.
Audit Metadata