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

google-meet

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the @useclawlink/cli package from the NPM registry. This is the official tool provided by the vendor (clawlink-hq).
  • [COMMAND_EXECUTION]: The skill executes shell commands to perform Google Meet actions via the CLI.
  • [DATA_EXFILTRATION]: The skill stores credentials locally at ~/.clawlink/credentials.json, following standard practices for CLI-based authentication.
  • [PROMPT_INJECTION]: The skill retrieves transcripts and participant data from Google Meet, creating an ingestion surface for indirect prompt injection.
  • Ingestion points: Actions such as googlemeet_get_transcript and googlemeet_list_participants (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: CLI commands to interact with Google Meet actions.
  • Sanitization: No specific sanitization logic is mentioned in the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:43 PM
Security Audit — agent-trust-hub — google-meet