find-your-level
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a
ROADMAP.mdfile from the author's repository on GitHub (fancyboi999/ai-engineering-from-scratch-zh) to retrieve curriculum data and time estimates. This is a legitimate functional requirement for generating personalized learning paths. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external source (
ROADMAP.md) to populate learning path tables. - Ingestion points: Fetches data from a remote URL via GitHub.
- Boundary markers: None identified in the prompt instructions for the ingested content.
- Capability inventory: The skill uses the ingested data to generate markdown tables and summary text. No dangerous subprocess or file-system write capabilities are invoked by the ingested data.
- Sanitization: No explicit sanitization or validation of the remote content is mentioned.
Audit Metadata