wecom-meeting-query
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes meeting titles and descriptions from an external system. If an attacker sets a malicious meeting title, the agent might execute embedded instructions when summarizing the meeting list.
- Ingestion points: Data is ingested from the
get_meeting_infotool output, specifically thetitleanddescriptionfields inSKILL.md. - Boundary markers: The instructions do not define boundary markers (like XML tags or specific delimiters) to separate meeting content from system instructions.
- Capability inventory: The skill uses the
wecom_mcptool for API interaction and command execution. - Sanitization: No sanitization or verification logic is present to filter executable instructions within the meeting metadata.
Audit Metadata