dx-devops-test-suite-run

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from a Salesforce organization, such as test execution status and error messages, which serves as an ingestion point for external data. \n
  • Ingestion points: API responses and query results from the DevopsTestSuiteExecution and DevopsTestExecution objects described in SKILL.md and references/polling-configuration.md. \n
  • Boundary markers: The instructions do not specify the use of delimiters when the agent processes data from the Salesforce org. \n
  • Capability inventory: The skill possesses the capability to execute shell commands via the Salesforce CLI (sf api request rest and sf data query) to interact with the org. \n
  • Sanitization: The instructions require the agent to translate technical error messages into plain language and avoid presenting raw JSON to the user. \n- [EXTERNAL_DOWNLOADS]: The skill requires the @salesforce/plugin-agent Salesforce CLI plugin. This is an official extension from a well-known service provider, documented neutrally as a functional prerequisite. \n- [COMMAND_EXECUTION]: The skill utilizes the Salesforce CLI to perform DevOps operations. All commands that mutate state are gated behind an explicit user confirmation prompt to ensure intended execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 06:35 PM
Security Audit — agent-trust-hub — dx-devops-test-suite-run