uplifting-components-to-slds2
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow requires the agent to execute shell commands using npx to run the SLDS linter on the local project directory.
- [EXTERNAL_DOWNLOADS]: The skill downloads the @salesforce-ux/slds-linter package from the public npm registry. This is a standard developer workflow using an official tool from a well-known vendor.
- [PROMPT_INJECTION]: The skill processes external data in the form of component source code, which introduces a surface for indirect prompt injection. 1. Ingestion points: Component CSS (.css), markup (.html), and Aura (.cmp) files. 2. Boundary markers: The instructions do not provide specific delimiters or ignore-instructions for the content of the refactored files. 3. Capability inventory: The skill has the ability to execute shell commands (npx). 4. Sanitization: There is no explicit sanitization or validation of the file content before it is processed by the agent.
Audit Metadata