google-meet
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill performs network requests to Google Meet's official API endpoints (
meet.googleapis.com). These operations are required for the skill's primary functionality and target a well-known service. - [COMMAND_EXECUTION]: The skill instructions provide examples using
curlandjqto interact with the API. It also references thezero doctorutility for troubleshooting the execution environment. - [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it processes untrusted data from external sources.
- Ingestion points: Meeting transcripts, participant names, and conference record data are retrieved from the Google Meet API into the agent context (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the documentation.
- Capability inventory: The skill facilitates network requests via
curland data manipulation viajq. - Sanitization: No evidence of sanitization or filtering of retrieved transcript text or participant-controlled fields was found.
Audit Metadata