google-meet-connector
Warn
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation references a quick-start Python script hosted on a GitHub repository ('github.com/firef1ie/OpenClawSkills') which is not associated with the primary vendor or a recognized trusted organization. Users should verify the contents of this external script before execution.\n- [PROMPT_INJECTION]: The skill ingests untrusted data from meeting transcripts and recordings, creating a surface for indirect prompt injection.\n
- Ingestion points: The actions 'get_transcript', 'get_recording', 'list_recordings', and 'list_transcripts' retrieve content from external Google services.\n
- Boundary markers: There are no explicit delimiters or instructions defined to prevent the agent from following commands embedded within the retrieved transcripts.\n
- Capability inventory: The skill has the ability to invoke external API calls and perform network operations via signed envelopes.\n
- Sanitization: No sanitization or validation of external transcript data is described in the instruction set.
Audit Metadata