spark-recipe-new-sender-review
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data (email content), which presents a surface for indirect prompt injection where an attacker might include malicious instructions within an email thread.
- Ingestion points: The agent reads external email threads using
spark thread <id>as described inSKILL.md. - Boundary markers: There are no explicit delimiters or instructions to the agent to disregard instructions found within the email content.
- Capability inventory: The skill utilizes the
sparkCLI tool to list emails, read threads, and modify sender statuses (accept/block). - Sanitization: No sanitization or validation mechanisms are specified for the email data before the agent reviews it.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various
sparkCLI commands to manage the email environment. - Evidence: Use of commands such as
spark emails Inbox --new-senders,spark thread <id>, andspark contact-action [accept/block]Contactare central to the skill's functionality.
Audit Metadata