sf-customers
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a set of architectural guidelines and implementation steps for Salesforce Commerce customer management. No malicious instructions, obfuscation, or unauthorized access attempts were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that involves fetching external documentation from the web, which creates an ingestion point for untrusted data.
- Ingestion points: The
WebSearchandWebFetchtools are used to retrieve documentation from Salesforce's official channels as specified inSKILL.md. - Boundary markers: The skill does not explicitly instruct the agent to use delimiters for the fetched content.
- Capability inventory: The skill has access to
Bash,Write,Edit, andWebSearchtools. - Sanitization: No specific sanitization or validation routines for external content are defined.
- Context: This finding is considered safe because the fetches target well-known, official documentation sources necessary for the skill's primary function, and the behavior aligns with the developer's stated purpose.
Audit Metadata