Skills
skills/agentscope-ai/copaw/cron/Gen Agent Trust Hub

cron

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for using the copaw CLI tool to manage recurring tasks. This includes commands to list, get, create, and delete cron jobs, which are forms of persistence. This behavior is the primary intended function of the skill.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection. When creating an 'agent' type task, the content provided in the --text parameter is stored and later interpreted as a prompt for the AI agent.
  • Ingestion points: The --text parameter in the copaw cron create command in SKILL.md.
  • Boundary markers: Absent; there are no delimiters or warnings to ignore embedded instructions in the scheduled text.
  • Capability inventory: The agent has the capability to execute commands via the copaw CLI tool as described in SKILL.md.
  • Sanitization: Absent; the skill does not specify any validation or filtering for the text content before it is scheduled.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 03:05 PM