agent-generator-tutor
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines an interaction model where user-provided text (answers to exercises and quizzes) is processed by the agent. This creates a surface for indirect prompt injection. This is a characteristic of the interactive teaching use case and does not represent an active threat in the context of this skill. * Ingestion points: User input passed to check_exercise and run_quiz methods described in SKILL.md. * Boundary markers: None visible in the documentation. * Capability inventory: Uses Read and Bash tools as specified in the allowed-tools configuration. * Sanitization: None visible in the documentation.
Audit Metadata