wecomcli-manage-schedule

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interacts with the enterprise system by executing the wecom-cli binary. It passes structured JSON data as arguments to perform operations like creating, updating, or deleting schedules.\n- [DATA_EXPOSURE]: The instructions include a dedicated privacy rule that explicitly forbids exposing internal userid strings to the user. It directs the agent to resolve these identifiers to human-readable names using a separate lookup skill, which is a security best practice for data minimization.\n- [INDIRECT_PROMPT_INJECTION]: The skill retrieves schedule summaries and descriptions that are user-controllable. This constitutes a potential indirect prompt injection surface where malicious instructions embedded in schedule data could attempt to influence agent behavior during processing.\n
  • Ingestion points: The get_schedule_detail API provides schedule titles and descriptions to the agent context.\n
  • Boundary markers: The instructions do not define specific delimiters to isolate retrieved schedule text from the agent's control logic.\n
  • Capability inventory: The agent has the ability to manage schedules (create, modify, cancel) and look up contacts using the provided CLI tools.\n
  • Sanitization: There are no instructions for the agent to sanitize or validate the content of the schedule summaries before processing them.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 05:33 PM