dx-lifecycle-center
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local bash scripts (
resolve-environment.sh,poll-deploy-status.sh) to perform environment lookups and status polling. These scripts are packaged with the skill and include alphanumeric validation on variables likerequestIdto mitigate shell injection risks. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Salesforce orgs via SOQL queries and REST API calls. This data (such as environment names and deployment logs) is used to update the agent's context. The skill provides instructions for normalizing this input to ensure consistent routing.
- [SAFE]: All network activity is performed through the
sfCLI targeting official Salesforce domains (*.salesforce.com,*.force.com). The skill does not perform any unauthorized data exfiltration or access sensitive local files like SSH keys or credentials.
Audit Metadata