skills/zhihaoairobotic/clawphd/cron/Gen Agent Trust Hub

cron

Warn

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • Persistence Mechanisms (MEDIUM): The skill is designed to maintain execution of instructions across sessions via a scheduler. While this is the primary purpose, it allows instructions to persist indefinitely. Evidence: Use of cron_expr and every_seconds to trigger recurring task execution.
  • Indirect Prompt Injection (LOW): The 'Task' mode executes instructions from the 'message' parameter without sanitization.
  • Ingestion points: 'message' parameter in 'cron' tool definition.
  • Boundary markers: Absent; no delimiters or instructions for the agent to ignore embedded commands.
  • Capability inventory: High; the agent is instructed to 'execute' the message, granting access to its suite of tools.
  • Sanitization: Absent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 18, 2026, 01:28 PM