cali-questions-quality
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions (SKILL.md) and a backup file (SKILL.md.bkp.md). There are no executable scripts (Python, JS, Shell), binary files, or configuration files that trigger code execution.
- [PROMPT_INJECTION]: No evidence of prompt injection or bypass attempts. The skill includes standard instructional language for an AI agent to perform a specific task (analyzing interview questions). The use of 'IMPORTANT' or 'Rule of Gold' (Regra de Ouro) is contextual to the methodology of the skill and does not target the agent's safety guardrails.
- [EXTERNAL_DOWNLOADS]: The skill does not contain any URLs, curl/wget commands, or package installation instructions. It is entirely self-contained within its markdown text.
- [DATA_EXFILTRATION]: No network access or sensitive file operations are present. The skill only processes text provided by the user in the conversation context.
- [SAFE]: The content is purely educational/methodological, focusing on the JTBD (Jobs to Be Done) and Cynefin frameworks for qualitative research. It provides guidelines for identifying ambiguity and improving question sequencing without any technical risk factors.
Audit Metadata