skills/hkuds/nanobot/cron/Gen Agent Trust Hub

cron

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPERSISTENCE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to schedule recurring tasks where a 'message' is provided as a task description to be executed later. This creates a surface where instructions from untrusted data could be persisted and executed by the agent.
  • Ingestion points: The message parameter in the cron tool and the content of HEARTBEAT.md referenced in the documentation.
  • Boundary markers: No boundary markers or 'ignore' instructions are suggested for the content of the scheduled tasks.
  • Capability inventory: The skill enables recurring agent task execution and notification delivery.
  • Sanitization: The documentation does not describe any sanitization or validation of the task descriptions before scheduling.
  • [PERSISTENCE]: The skill provides functionality for scheduling recurring tasks and reminders, which is a mechanism to maintain persistent agent activity and automated execution across different chat sessions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 08:19 AM