skills/letta-ai/lettabot/cron/Gen Agent Trust Hub

cron

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes lettabot-cron and lettabot-message command-line utilities. These tools are recognized as legitimate vendor resources originating from the author 'letta-ai'.
  • [PROMPT_INJECTION]: The skill establishes a scheduling mechanism where predefined messages are processed by the agent at set times. Although this creates a surface for indirect prompt injection, the skill employs structured message headers (e.g., [cron:ID Name]) and provides the agent with explicit context (current time, job metadata), which serves as a boundary marker to help the agent distinguish automated tasks from direct user instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 11:40 PM