wecom-schedule

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses a dedicated MCP tool (wecom_mcp) for all interactions with the WeCom environment. All operations are scoped to schedule management and follow standard interaction patterns without any unauthorized access attempts.- [PROMPT_INJECTION]: Evaluation of the indirect prompt injection surface for this skill:
  • Ingestion points: Schedule metadata (summaries, descriptions, and locations) retrieved from the WeCom system via the get_schedule_detail and check_availablity interfaces.
  • Boundary markers: None explicitly defined in the prompts to separate fetched data from instructions.
  • Capability inventory: Modification of existing data (update_schedule), deletion of schedules (cancel_schedule), and contact lookup for organizational users (wecom-contact-lookup).
  • Sanitization: The skill incorporates mandatory human-in-the-loop confirmation steps for all destructive or creative operations (create, update, cancel), which serves as a robust control against the automated execution of instructions that might be embedded in schedule data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 04:45 PM