experience-ui-bundle-agentforce-client-generate

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Salesforce CLI (sf) commands to perform legitimate development tasks. Specifically, it executes sf org display to check connectivity and sf data query to retrieve metadata (Bot IDs and status) from the user's authenticated Salesforce environment. These operations are scoped to agent discovery and project configuration.
  • [EXTERNAL_DOWNLOADS]: The instructions facilitate the installation of official Salesforce development tools and libraries, including @salesforce/cli and @salesforce/ui-bundle-template-feature-react-agentforce-conversation-client. These downloads originate from standard registries and belong to a known, trusted vendor ecosystem.
  • [PROMPT_INJECTION]: The skill contains strict validation logic and deterministic rules (e.g., the 18-character Agent ID regex ^0Xx[a-zA-Z0-9]{15}$) that prevent the agent from accepting malformed or suspicious identifiers. It emphasizes following documented component props and explicitly forbids improvising alternatives.
  • [DATA_EXFILTRATION]: There is no evidence of unauthorized data transmission. The skill interacts with the user's local filesystem and Salesforce org to synchronize configuration, ensuring that sensitive metadata like Agent IDs are used only within the project's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 12:31 PM
Security Audit — agent-trust-hub — experience-ui-bundle-agentforce-client-generate