skills/forcedotcom/afv-library/implementing-ui-bundle-agentforce-conversation-client/Gen Agent Trust Hub
implementing-ui-bundle-agentforce-conversation-client
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is authored by a recognized vendor and focuses on the integration of official Salesforce UI components.
- [EXTERNAL_DOWNLOADS]: The skill manages dependencies using the
@salesforcescoped registry on NPM, which is an established and trusted source for Salesforce-related development tools. - [COMMAND_EXECUTION]: Local shell commands are limited to standard file discovery using
grepand package management vianpm, both of which are typical for front-end development tasks. - [DATA_EXPOSURE]: The skill handles the Salesforce
agentId. This identifier is a public-facing configuration value for the chat component and is subject to strict regex validation (^0Xx[a-zA-Z0-9]{15}$) before being used. - [INDIRECT_PROMPT_INJECTION]: While the skill processes project files and user input, it operates within a well-defined schema for React components and uses explicit validation for sensitive parameters like the agent ID, reducing the risk of malicious data influencing agent behavior.
Audit Metadata