prompt-design
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- PROMPT_INJECTION (SAFE): While the skill contains instructions on how to structure prompts, it does not include patterns aimed at overriding the agent's safety protocols or extracting system information. The use of 'IMPORTANT' or 'CRITICAL' in the documentation is for instructional clarity, not for bypassing constraints.
- DATA_EXFILTRATION (SAFE): No file system access or network requests are present in the provided files.
- REMOTE_CODE_EXECUTION (SAFE): The skill contains no scripts or commands that download or execute external code.
- OBFUSCATION (SAFE): All content is in clear text with no encoded strings or hidden characters.
- INDIRECT_PROMPT_INJECTION (LOW): As a prompt design tool, the skill naturally processes user-provided prompts. However, it lacks executable capabilities (like file writing or network access), meaning the risk of an injection causing side effects is negligible.
Audit Metadata