platform-widget-generate
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is authored by a trusted vendor and implements standard automation for Salesforce development workflows.
- [COMMAND_EXECUTION]: The skill provides instructions for using the Salesforce CLI (sf) to interact with the platform. It includes explicit security constraints for the AI agent to avoid unsafe shell patterns like backticks, subshells, and dynamic execution (eval/exec), ensuring the commands remain within safe boundaries.
- [CREDENTIALS_UNSAFE]: The skill includes proactive security instructions that forbid the agent from extracting or displaying sensitive environment credentials, such as organization access tokens.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from Apex classes and user prompts (Ingestion points: user input, local .cls files). While it lacks explicit boundary markers for these sources, it provides sanitization capabilities (Sanitization: HTMLENCODE, JSENCODE) and interacts with the environment through restricted CLI calls (Capabilities: sf cli, file writing).
Audit Metadata