platform-sandbox-configure

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the official Salesforce CLI (sf) to perform environment management tasks. This includes listing, creating, refreshing, and deleting sandboxes. These operations are consistent with the skill's stated purpose and the author's identity (forcedotcom).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Salesforce API responses, such as sandbox names and descriptions. This represents an attack surface for indirect prompt injection. However, the risk is mitigated by instructions to the agent to report API results verbatim without interpretation and to escape single quotes in free-text fields before interpolating them into CLI commands.
  • [SAFE]: The skill implements mandatory human-in-the-loop confirmation for all irreversible actions (Create, Activate, Discard, Delete, and Refresh with AutoActivate). This prevents accidental or autonomous execution of high-impact operations.
  • [SAFE]: The skill adheres to the principle of least privilege by specifying the required ManageSandboxes permission in its metadata and logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 10:19 AM