Skills
Navigate
skills/readdle/spark-cli-skills/spark-recipe-vacation-catchup/Gen Agent Trust Hub

spark-recipe-vacation-catchup

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading email threads, creating a surface for indirect prompt injection.
  • Ingestion points: SKILL.md (Step 3) uses spark thread <id> to read email content.
  • Boundary markers: Absent. There are no instructions or delimiters provided to prevent the agent from executing instructions found within email bodies.
  • Capability inventory: The skill utilizes spark action archive, spark contact-action blockContact, and spark action snooze in SKILL.md.
  • Sanitization: Absent. No mention of content sanitization or filtering is present.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:07 PM
Security Audit — agent-trust-hub — spark-recipe-vacation-catchup