life-sciences-prerequisites-validate
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
sfCLI tool to execute read-only queries against a Salesforce environment. All commands are standard administrative queries (sf org display,sf data query) used to retrieve configuration status. - [REMOTE_CODE_EXECUTION]: There is no evidence of remote script execution or dynamic code injection. All logic is driven by static Salesforce SOQL and Tooling API queries defined within the reference files.
- [CREDENTIALS_SAFE]: The skill does not handle or store raw credentials. It relies on the existing authentication context of the
sfCLI (--target-org) and includes a prerequisite step to ensure the user is authenticated before proceeding. - [DATA_EXPOSURE]: Data access is limited to org metadata (feature toggles, sharing models, and package installation status). It does not access sensitive business data, and there are no network operations to exfiltrate the retrieved metadata.
- [PRIVILEGE_ESCALATION]: The skill explicitly states it will not automatically enable or configure settings. It acts as a validator only, requiring the user to manually perform remediation steps through the Salesforce Setup UI.
- [PROMPT_INJECTION]: The skill contains clear scope definitions and 'off-topic' request handling to prevent the agent from deviating from its primary purpose of validation.
Audit Metadata