check-understanding
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches course curriculum and documentation from the author's public GitHub repository (
github.com/fancyboi999/ai-engineering-from-scratch-zh) to provide quiz content when local files are unavailable.- [INDIRECT_PROMPT_INJECTION]: The skill processes external lesson content to generate interactive quiz questions, creating a potential surface for indirect prompt injection if the source material were to be compromised. - Ingestion points: Remote Markdown files from the author's repository and local files in the
phases/directory are read into the agent's context. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested lesson content.
- Capability inventory: The skill performs text generation and interactive questioning; it does not possess capabilities for code execution, system modification, or unauthorized network communication.
- Sanitization: No sanitization or filtering is applied to the fetched lesson content before it is used for question generation.
Audit Metadata