Phase quiz for AI Engineering from Scratch. Trigger with "quiz me", "test phase", "check my understanding", "do I know phase 3", or `/check-understanding <phase>`.
72
89%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
At runtime the workflow reads lesson teaching material by fetching `docs/en.md` files from the GitHub raw base URL (and potentially from the local `phases/` directory), so outsider-authored content in repo files can be ingested when generating questions.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill explicitly fetches runtime lesson content from https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/README.md (and associated raw lesson docs) and uses that content to generate the quiz prompts, so the external URL directly controls agent prompts.
39ea8a1
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.