spark-persona-exec-assistant
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from incoming emails, creating a surface for indirect prompt injection. Malicious instructions contained within an email could potentially influence the agent's actions during briefings or drafting processes.
- Ingestion points: The agent retrieves email headers and thread content via the
spark emailsandspark threadcommands defined inSKILL.md. - Boundary markers: The instructions lack delimiters or explicit directives for the agent to ignore instructions embedded in the external email data.
- Capability inventory: The skill has the capability to create drafts (
spark draft), search contacts, and view calendar events. - Sanitization: No mechanism for sanitizing or validating the contents of the retrieved emails is described.
Audit Metadata