wecomcli-edit-meeting

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to interact with the Enterprise WeChat API via a specific command-line interface (wecom-cli). The operations are restricted to meeting cancellation and member management.\n- [COMMAND_EXECUTION]: The skill employs structured command execution using the wecom-cli binary. Parameters are passed as JSON strings, and there is no evidence of shell injection or unsafe argument handling.\n- [PROMPT_INJECTION]: The instructions do not contain any patterns intended to override agent behavior, bypass safety protocols, or leak system prompts.\n- [DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were identified. The skill correctly identifies the need to fetch meeting and contact information through appropriate helper skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 05:32 PM