interactive-textbook
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The workflow section directs the agent to initialize a local repository using standard development tools including Vite, React, TypeScript, and Tailwind CSS. This involves routine shell commands for project scaffolding and dependency installation.
- [PROMPT_INJECTION]: The skill processes user-supplied source text to generate textbook components, which presents a surface for indirect prompt injection. This is a functional requirement for the skill's operation. 1. Ingestion points: User-provided source text as input for component generation. 2. Boundary markers: None defined within the skill instructions. 3. Capability inventory: The agent has the ability to execute commands and write files to manage the textbook repository. 4. Sanitization: No specific input sanitization or validation logic is specified in the instructions.
Audit Metadata