scoping-agent-user-permissions
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute Salesforce CLI (
sf) commands to query field metadata, deploy permission set files, and assign permissions to users within the Salesforce environment.- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by instructing the agent to process data from Salesforce objects such asClaim,Account, andInsurancePolicy. - Ingestion points: Data from Salesforce objects retrieved via the
sfCLI or Salesforce API as defined inSKILL.md. - Boundary markers: Absent; there are no delimiters or instructions provided to the agent to ignore or isolate potentially malicious instructions within the retrieved CRM data.
- Capability inventory: The skill utilizes subprocess execution of the Salesforce CLI (
sf) for querying, deployment, and permission management. - Sanitization: Absent; no validation, escaping, or filtering of retrieved Salesforce data is specified in the instructions.
Audit Metadata