recipe-triage-security-alerts

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the gws CLI tool to perform alert management tasks.\n
  • Evidence: The skill defines steps to run gws alertcenter alerts list, gws alertcenter alerts get, and gws alertcenter alerts undelete.\n
  • Context: These commands are consistent with the skill's stated purpose and use a tool that is identified as a vendor-owned resource for the author 'googleworkspace'.\n- [PROMPT_INJECTION]: The skill facilitates the retrieval of data from the Google Workspace Alert Center, which is a potential surface for indirect prompt injection.\n
  • Ingestion points: Security alert data is ingested when listing and viewing alert details.\n
  • Boundary markers: The skill uses the --format table flag, providing structural separation for the ingested data.\n
  • Capability inventory: The skill's capabilities are restricted to reading alerts and performing basic management actions (undelete) through the CLI.\n
  • Sanitization: Content is retrieved directly from the trusted Google Workspace environment via the official CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 10:50 PM