skills/franky47/dotfiles/scheduler/Gen Agent Trust Hub

scheduler

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the system date command to synchronize the agent's internal time context with the host system. This ensures that relative time calculations (e.g., "in 10 minutes") are accurate before generating cron expressions.
  • [PROMPT_INJECTION]: The skill implements a scheduling system that accepts user-defined prompts for later execution, creating an indirect prompt injection surface.
  • Ingestion points: The prompt argument passed to the schedule tool.
  • Boundary markers: Absent; scheduled prompts are treated as fresh standalone instructions.
  • Capability inventory: Access to the system date command and the task management schedule tool.
  • Sanitization: No sanitization of scheduled prompt content is mentioned or implemented in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 02:50 AM
Security Audit — agent-trust-hub — scheduler