The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill generates quiz content by reading external data such as code diffs (git diff) or documents provided by the user. While this creates an attack surface where malicious instructions embedded in the source material could theoretically influence the agent, the risk is negligible as the skill only performs read operations and asks questions without executing code or exfiltrating data.
Ingestion points: Processes git diff output and user-specified files or documentation.
Boundary markers: No specific delimiters are defined to separate ingested data from quiz instructions.
Capability inventory: Accesses file content and uses the AskUserQuestion tool to interact with the user.
Sanitization: No explicit sanitization or filtering of the ingested content is mentioned.

quiz-me