elaborative-interrogation-generator
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by directly embedding user-controlled variables into the system instructions. \n- Ingestion points: User inputs for variables such as topic, student_level, content_text, and learning_objectives in SKILL.md are directly interpolated into the core prompt. \n- Boundary markers: No protective delimiters or clear instructions are present to differentiate user-provided data from system instructions, which could allow a user to override agent behavior. \n- Capability inventory: The skill is limited to text generation and does not have access to sensitive tools, file system operations, or network requests. \n- Sanitization: No input validation or content filtering is performed on the data before it is processed by the model.
Audit Metadata