automations

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEPERSISTENCEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [PERSISTENCE]: The skill is designed to manage recurring tasks through the schedule_automation tool, which allows prompts to be executed automatically at specific intervals or times. This creates a native persistence mechanism within the Local Studio environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from previous automation runs, which may contain untrusted content.\n
  • Ingestion points: The read_automation tool (SKILL.md) retrieves the full history and reported outcomes of the last 20 runs of an automation.\n
  • Boundary markers: The instructions do not define delimiters or specific instructions for the agent to ignore or sanitize embedded commands within the history data.\n
  • Capability inventory: The skill provides tools to create (schedule_automation), modify (update_automation), and immediately trigger (run_automation_now) prompt-based tasks across sessions (SKILL.md).\n
  • Sanitization: No sanitization, filtering, or validation steps are mentioned for the content retrieved from the automation history store.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 09:31 AM
Security Audit — agent-trust-hub — automations