language-learning-notebook
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input from lessons, tutor sessions, and phrases 'heard in the wild' to generate notebook entries. If this material contains malicious instructions, it could potentially influence the agent's behavior during the transformation process or affect downstream agents that process the saved notes.
- Ingestion points: User-provided notes, material, and screenshots described in the 'What to ask for' section.
- Boundary markers: The instructions do not specify the use of clear delimiters (e.g., XML tags or triple quotes) when the agent processes the untrusted input material.
- Capability inventory: The skill is designed to format text into Markdown and suggests calling external note-saving tools (e.g., 'Scratchpad connector') to persist data.
- Sanitization: The instructions focus on linguistic accuracy and labeling added examples but do not include technical sanitization or escaping of the input data to prevent prompt injection.
Audit Metadata