Skills
skills/readdle/spark-cli-skills/spark-recipe-draft-batch/Gen Agent Trust Hub

spark-recipe-draft-batch

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses the spark tool for its intended purpose of email management. No unauthorized data access, network exfiltration, or credential harvesting patterns were detected.
  • [PROMPT_INJECTION]: The skill reads email content, which is an external ingestion point for potential indirect prompt injection. This is considered safe as the workflow requires human review of each decision. 1. Ingestion points: Email threads via spark thread <id> in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Draft editing and deletion via spark commands in SKILL.md. 4. Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 01:15 PM