spark-recipe-stakeholder-brief

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses the spark CLI to retrieve user data (emails, meetings, contacts) for summarizing relationship history. These are legitimate operations for the Spark email ecosystem.
  • [PROMPT_INJECTION]: The skill processes untrusted data from external sources, presenting an indirect prompt injection surface.
  • Ingestion points: The skill reads external content via spark emails, spark thread, and spark meeting commands in SKILL.md.
  • Boundary markers: No boundary markers or specific instructions to isolate external data are present.
  • Capability inventory: The skill uses spark CLI for data retrieval; it does not contain capabilities for file writing or outbound network requests.
  • Sanitization: No sanitization of external content is performed before interpolation into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 11:19 AM