salesforce

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (SAFE): The skill defines an ingestion surface for CRM record data and query criteria. This is a standard functional requirement for Salesforce integration and does not contain evidence of malicious redirection or instruction overriding.
  • [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, API keys, or access to sensitive local file paths (e.g., SSH keys, AWS credentials) were found.
  • [Remote Code Execution] (SAFE): The skill uses the Refly CLI platform tools. There are no attempts to download and execute arbitrary scripts or install untrusted third-party packages.
  • [Obfuscation] (SAFE): All content is provided in clear text with no evidence of Base64 encoding, zero-width characters, or homoglyph-based evasion techniques.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:35 PM