ux-ui-map-page-by-page
Warn
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the AI agent to execute a local JavaScript script located at
scripts/page_artifacts.mjsusing thenodeenvironment. The instructions provide specific commands for scaffolding and validating the directory structure and files generated during the UI mapping process. While these scripts are intended as helper tools, executing local code is a sensitive operation. - [PROMPT_INJECTION]: This skill is vulnerable to indirect prompt injection because it navigates to external web routes and captures screenshots for analysis. Malicious content on a scanned web page could attempt to influence the agent's documentation or analysis output.
- Ingestion points: External web routes and captured UI screenshots (as defined in
SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided for the data captured from web routes.
- Capability inventory: The agent has the capability to write files to the local filesystem (
ux_ui_map/directory) and execute local scripts (node scripts/page_artifacts.mjs). - Sanitization: There is no evidence of sanitization or validation of the data extracted from the web routes before it is used to generate documentation or analysis requests.
Audit Metadata