implementing-ui-bundle-agentforce-conversation-client

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes discovery commands such as grep to identify current usage of the conversational client in the project.
  • [EXTERNAL_DOWNLOADS]: Downloads and installs the official @salesforce/ui-bundle-template-feature-react-agentforce-conversation-client package from the npm registry. This is a standard dependency for the skill's intended functionality.
  • [DATA_EXFILTRATION]: Accesses and reads application source code files to determine current properties and implement requested modifications.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted data from the user's project.
  • Ingestion points: File contents and grep search results are ingested into the agent context (SKILL.md).
  • Boundary markers: No specific delimiters or boundary markers are defined to prevent the agent from obeying instructions hidden within project files.
  • Capability inventory: The skill can modify source code and execute package management commands (SKILL.md).
  • Sanitization: There is no explicit sanitization or validation of the project data before it is interpolated into instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 01:00 AM
Security Audit — agent-trust-hub — implementing-ui-bundle-agentforce-conversation-client