sf-datacloud-harmonize
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple Salesforce CLI commands (sf data360 ...) and a local JavaScript file (node ~/.claude/skills/sf-datacloud/scripts/diagnose-org.mjs) to perform harmonization tasks and org diagnostics as documented in SKILL.md.
- [EXTERNAL_DOWNLOADS]: The skill requires an 'external community sf data360 CLI plugin', which is a third-party dependency not provided or verified within the skill itself.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from external Salesforce organizations and uses this data to inform its operations. Ingestion points: sf data360 dmo list, sf data360 query describe (SKILL.md). Boundary markers: No specific delimiters or instructions to ignore embedded content are used. Capability inventory: Shell command execution via sf CLI and Node.js script execution (SKILL.md). Sanitization: No explicit data sanitization or validation of the retrieved Salesforce schema is documented.
Audit Metadata