Skills
Navigate
skills/orcaqubits/agentic-commerce-skills-plugins/sf-b2c-cartridges/Gen Agent Trust Hub

sf-b2c-cartridges

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to fetch live documentation and search results from external sources to ensure up-to-date information. Processing this external data presents a theoretical surface area for indirect instructions. \n
  • Ingestion points: WebSearch queries and WebFetch of documentation from developer.salesforce.com. \n
  • Boundary markers: Absent; the skill does not specify delimiters for the fetched content. \n
  • Capability inventory: The skill has access to Write, Edit, and Bash tools, which could be leveraged if malicious instructions were successfully injected through external documentation. \n
  • Sanitization: Not present. \n
  • [EXTERNAL_DOWNLOADS]: The skill references and encourages fetching resources from developer.salesforce.com and the SFRA repository. These are official and trusted sources for Salesforce Commerce Cloud developers.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 06:33 PM