design-from-app
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The scripts
scripts/compare.ps1andscripts/measure.ps1use the PowerShellAdd-Typecmdlet to compile and execute embedded C# code at runtime. This code is used for performance-critical image manipulation tasks such as pixel-level comparison and measurement. While this involves dynamic compilation, it is directly related to the skill's primary purpose of visual analysis. \n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external screenshots provided by the user. If these images contain text or patterns specifically designed to override agent instructions, they could influence the agent's behavior during the measurement and kit-building phases. \n - Ingestion points: PNG screenshots stored in the
design/reference/directory. \n - Boundary markers: Absent; the instructions do not specify any delimiters or safety warnings for the data extracted from the images. \n
- Capability inventory: The agent can execute local PowerShell scripts, read system files, and write design documents and images. \n
- Sanitization: Absent; there is no evidence of filtering or validation of the text or visual data extracted from the screenshots. \n- [COMMAND_EXECUTION]: The skill requires the execution of local PowerShell scripts to perform its core functions. These scripts interact with the local file system to read screenshots and write comparison results.
Audit Metadata