prompt-engineering
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill contains examples of prompt injection strings (e.g., 'Ignore all previous instructions', 'DAN') within a dedicated 'Common Mistakes' section. These are provided for educational purposes to illustrate vulnerabilities and demonstrate how to craft defensive system prompts.- [COMMAND_EXECUTION]: Includes a Python helper function 'extract_json' designed to parse JSON content from strings using regular expressions and the standard 'json' library. The function does not perform any dangerous operations such as arbitrary code execution or network requests.
Audit Metadata