gws-meet
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the 'gws' binary to be installed on the host system to execute API calls for Google Meet.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the retrieval of meeting-related data, such as transcripts and smart notes, which originate from external participants.
- Ingestion points: The skill ingests external content through the
conferenceRecords transcriptsandconferenceRecords smartNotesmethods. - Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted transcript data from the agent's internal logic.
- Capability inventory: The agent has the ability to execute shell commands via the
gwsbinary and manage meeting spaces. - Sanitization: No sanitization or validation of the retrieved transcript text is described in the skill instructions.
Audit Metadata