chat-customizations-editor
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
npx @playwright/cli evalto execute JavaScript snippets within the browser context for debugging layout and inspecting widgets. These actions are consistent with the skill's purpose as a development tool for the management UI. - [PROMPT_INJECTION]: The skill facilitates the management of potentially untrusted data such as AI skills, prompts, and hooks, creating a surface for indirect prompt injection.
- Ingestion points: The UI processes
IAgentSkillobjects,IChatPromptSlashCommanddefinitions, and prompt files retrieved vialistPromptFilesas described in SKILL.md. - Boundary markers: The provided documentation does not specify the use of delimiters or boundary markers to separate customization content from system instructions.
- Capability inventory: The skill allows for command execution via
Bashfor running tests (./scripts/test.sh) and UI automation tools (npx @playwright/cli). - Sanitization: The documentation focuses on UI components and does not describe validation or sanitization routines for the processed customization data.
Audit Metadata