polling-test-results

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the sf data query command to retrieve test status and results from a Salesforce org. This is the primary intended functionality and uses the official Salesforce CLI tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Salesforce records (fields such as Status, TestsRan, and CoveragePercentage from the DevopsTestExecution object). While this constitutes an ingestion of external data that is subsequently processed by the agent, the risk is minimal as the data is structured and originates from the user's own Salesforce environment. The skill identifies the ingestion points and uses the retrieved data to decide whether to continue polling or surface results.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 08:28 PM
Security Audit — agent-trust-hub — polling-test-results