salesforce-data-handling
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill provides legitimate code for managing Salesforce data privacy.
- [SAFE]: The inclusion of a data redaction function (redactSfRecord) for logs demonstrates a commitment to security best practices.
- [SAFE]: While the skill interacts with PII, this is consistent with its stated purpose of assisting with GDPR/CCPA compliance and DSAR requests.
- [SAFE]: An ingestion surface for Indirect Prompt Injection exists via Salesforce record queries (conn.query in SKILL.md), but the risk is low due to the lack of dangerous sinks like eval or shell execution. Evidence Chain: Ingestion points: SKILL.md; Boundary markers: None; Capability inventory: Read, Write, Edit tools; Sanitization: redactSfRecord logic implemented in Step 5.
Audit Metadata