check-understanding

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches educational content and phase metadata from the author's repository on GitHub (rohitg00/ai-engineering-from-scratch) when local course files are not available. This is used solely for generating quiz questions.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes external markdown documentation to generate quiz questions.
  • Ingestion points: Retrieves README.md and lesson en.md files from the remote repository or reads local phases/ documentation.
  • Boundary markers: None specified in the instructions to separate content from instructions during the generation of the 8 questions.
  • Capability inventory: Reading local files, fetching content via HTTP GET, and interactive user prompting via AskUserQuestion.
  • Sanitization: No explicit sanitization or filtering of the retrieved markdown content is defined before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:51 PM
Security Audit — agent-trust-hub — check-understanding