skills/clawlink-hq/skills/google-meet/Gen Agent Trust Hub

google-meet

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFECREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The documentation specifies that authentication credentials are stored at ~/.clawlink/credentials.json. While standard for CLI operation, this local path is accessible to the agent.\n- [EXTERNAL_DOWNLOADS]: The skill uses npx @useclawlink/cli to download and run the vendor's command-line interface from the NPM registry. These resources originate from the skill author's infrastructure.\n- [COMMAND_EXECUTION]: Interaction with Google Meet is performed through shell commands using the ClawLink CLI to list, read, and create meeting data.\n- [INDIRECT_PROMPT_INJECTION]: The skill retrieves conference transcripts and participant entries which are untrusted external inputs.\n
  • Ingestion points: Conference transcripts, record entries, and participant sessions retrieved from Google Meet.\n
  • Boundary markers: Absent; the instructions do not define delimiters for external data.\n
  • Capability inventory: Subprocess execution for creating, updating, and ending meetings.\n
  • Sanitization: No validation or sanitization of conference content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 05:45 PM