study-quiz
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest a user-specified theme and difficulty level to generate quiz content. This design creates an attack surface where malicious input provided as a theme could attempt to influence the agent's subsequent instructions.
- Ingestion points: User input for the 'tema' (theme) variable extracted in
SKILL.md(Step 1). - Boundary markers: The instructions lack explicit delimiters or instructions to ignore nested commands within the 'tema' variable during the quiz generation phase.
- Capability inventory: The skill uses the
AskUserQuestiontool for interaction; it does not request file system access or network capabilities. - Sanitization: No sanitization or validation logic for the input theme is defined.
Audit Metadata