gmail
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes content from external email senders.
- Ingestion points: The tools
read_email,get_email_thread,list_emails, andsearch_emails(SKILL.md) ingest content from untrusted third parties. - Boundary markers: There are no instructions for the agent to use specific delimiters or ignore instructions found within email bodies.
- Capability inventory: The skill provides tools for sending emails (
send_email) and deleting messages (bulk_delete_emails), which could be abused if an injection is successful. - Sanitization: The skill does not define any sanitization or validation logic for the content of processed emails.
- [SAFE]: The functionality provided is appropriate for the skill's purpose, and it is authored by a recognized organization. The skill includes built-in safety requirements, such as mandating user confirmation and a stated reason for permanent bulk deletions.
Audit Metadata