email-register
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from incoming email content to generate replies or edits, creating a surface for indirect prompt injection.
- Ingestion points: Incoming email threads and pasted text processed in the 'Replying to incoming' and 'Editing existing text' workflows in SKILL.md.
- Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands in the email text.
- Capability inventory: The skill utilizes Gmail tools (create_draft, list_drafts, search_threads) for mailbox interaction.
- Sanitization: No evidence of sanitization for ingested email content is present in the instructions.
Audit Metadata