learn-quiz
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and generate questions from code worked with by the user, creating a surface where malicious instructions in that code could influence the agent. Ingestion points: The agent is instructed in SKILL.md to 'Identify the last code I worked with' for the quiz context. Boundary markers: There are no explicit delimiters or instructions to ignore nested directives within the analyzed code. Capability inventory: The skill is restricted to natural language generation for quiz questions and does not utilize file-system, network, or subprocess tools. Sanitization: No input sanitization or filtering of the code content is specified before processing.
- [NO_CODE]: The skill does not contain any executable scripts, binaries, or configuration files, consisting solely of markdown instructions.
Audit Metadata