Skills
skills/dtyq/magic/using-cron/Gen Agent Trust Hub

using-cron

Warn

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: MEDIUMPROMPT_INJECTIONDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructions in SKILL.md use strong imperative language ("CRITICAL", "MUST", "NEVER") to prioritize this skill and override agent decision-making when future time intents are detected.
  • [DATA_EXFILTRATION]: The utility script scripts/_context.py reads sensitive configuration and history files located at .credentials/init_client_message.json and .chat_history/magic<main>.session.json to retrieve session identifiers.
  • [COMMAND_EXECUTION]: The skill documents and requires the use of shell tools to execute local Python scripts for core functionality.
  • [DATA_EXFILTRATION]: The skill transmits extracted session metadata and user-provided task descriptions to a remote service through a specialized SDK.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 28, 2026, 10:28 AM
Security Audit — agent-trust-hub — using-cron