snowflake-to-bigquery-converter

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the looker-cli tool to interact with Looker instances. It executes commands such as looker-cli project checkout, looker-cli project file ls, and looker-cli project file cat to retrieve and analyze LookML files. These operations are restricted to project auditing and migration reporting.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes the content of LookML files provided by the user via the CLI.
  • Ingestion points: LookML file content is retrieved in SKILL.md using the looker-cli project file cat command.
  • Boundary markers: The instructions do not specify explicit delimiters for the ingested file content during the analysis phase.
  • Capability inventory: The skill uses looker-cli subcommands for authentication, project navigation, and file retrieval.
  • Sanitization: The skill identifies SQL patterns and generates a human-readable migration report. It does not automatically execute the resulting SQL or write back to the project without user intervention.
  • [EXTERNAL_DOWNLOADS]: The skill refers users to the official looker-cli GitHub repository (github.com/looker-open-source/looker-cli) for installation and authentication guidelines. These references target the tool's source code and documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 06:35 AM