sf-b2c-sfra

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches reference source code and architectural patterns from the official Salesforce Commerce Cloud repository on GitHub.
  • [INDIRECT_PROMPT_INJECTION]: The skill creates an ingestion surface by instructing the agent to fetch live documentation and perform web searches on official Salesforce developer domains. 1. Ingestion points: WebFetch and WebSearch operations targeting GitHub and developer.salesforce.com (SKILL.md). 2. Boundary markers: None specified. 3. Capability inventory: Read, Write, Edit, Bash, Grep, Glob, WebSearch, and WebFetch tools listed in frontmatter (SKILL.md). 4. Sanitization: The skill does not provide specific instructions for sanitizing external documentation before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 06:34 PM