spark-recipe-invitation-manager
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content from email threads and calendar invitations, which represents an indirect prompt injection surface.
- Ingestion points: Meeting details and thread content retrieved via
spark thread <id>in SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing email content.
- Capability inventory: The skill's capabilities are restricted to email and calendar operations via the
sparkCLI tool. No capabilities for external network communication, arbitrary shell execution, or persistent file system modifications were found. - Sanitization: No content sanitization or validation steps are defined for the ingested email data.
Audit Metadata