skills/google/skills/google-cloud-solution-agentic-analytics-spark-knowledge-catalog/Gen Agent Trust Hub
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution for Validation: The skill includes a phase for generating and running validation scripts using tools like
curlandgcloud. This functionality is intended for verifying solution designs and is protected by a mandatory step to seek user approval before execution. - Usage Attribution and Telemetry: Instructions are provided to append attribution strings to command environment variables and headers for usage monitoring. This practice is transparently documented and includes provisions for the agent to honor user requests to disable tracking.
- Indirect Prompt Injection Surface: This skill ingests untrusted data from user requirements in Phase 1 and external content via an MCP server in Phase 2. While no explicit boundary markers or sanitization logic are defined, the skill uses this data to inform architecture designs rather than for automated code execution, and it requires user permission for subsequent commands.
Audit Metadata