sam-uren-cowork-mac
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the SAM web interface, specifically project names and descriptions, which are then used as context for processing user instructions. While this represents an external data ingestion surface, the source is an authenticated internal business application (sam.surf.nl), making the risk of adversarial injection negligible.
- [DYNAMIC_EXECUTION]: The skill generates and executes JavaScript snippets at runtime to interact with the browser's Document Object Model (DOM). This includes reading table rows and simulating user clicks. These scripts follow standard templates and are used solely for the intended purpose of automating the web interface.
- [COMMAND_EXECUTION]: The skill utilizes the Control Chrome MCP to navigate the browser and execute scripts. All actions are scoped to the legitimate SURF time-tracking domain (sam.surf.nl).
Audit Metadata