prompt-engineer
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of a Markdown file (SKILL.md) providing instructional content. There are no scripts, binaries, or automated tools included.- [SAFE]: The content is purely educational, detailing standard AI prompting techniques such as 'Chain of Thought' and 'Few-shot' prompting. No evidence of malicious behavior, data exfiltration, or external network access was found.- [PROMPT_INJECTION]: While the skill describes role-playing and instructional techniques (e.g., '당신은 10년 경력의 한국 세무사입니다'), these are presented as best practices for eliciting better AI performance and do not target the agent's underlying safety protocols or system instructions.
Audit Metadata