skills/sshvarzman-salesforce/claude-skills/building-omnistudio-integration-procedure/Gen Agent Trust Hub
building-omnistudio-integration-procedure
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted user requirements to generate Salesforce Integration Procedure JSON and CLI commands.
- Ingestion points: User-defined business purposes, target objects, and naming conventions in SKILL.md.
- Boundary markers: None identified; the skill lacks explicit delimiters for user content.
- Capability inventory: Execution of Salesforce CLI (sf) commands for metadata deployment and REST API calls for record creation.
- Sanitization: Includes a 110-point validation report that audits for hardcoded credentials and basic input validation.
Audit Metadata