insights-workbook-cli

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill leverages the frappectl CLI tool to interact with Frappe Insights sites. It uses subprocess.run() within the build_workbook.py script to execute these commands, which is the intended and documented method for managing the service.
  • [EXTERNAL_DOWNLOADS]: The skill instructions guide the user to install the frappectl utility and clone the frappe/insights repository. These are legitimate resources maintained by the skill's author ('frappe') and are necessary for the skill's operation.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Insights sites, such as existing workbook titles and query definitions, to assist in authoring new content. To mitigate potential risks from untrusted data, the skill mandates a 'scope block' step where the agent must present its plan to the user for approval before performing any write operations. It also includes a robust verification script to ensure the integrity of the generated workbooks.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 11:18 AM