prompt-engineering-patterns

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary focus is on documentation and best practices for prompt engineering. All code snippets and the included script serve legitimate educational and developmental purposes.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface through the use of variable interpolation in its prompt templates and the scripts/optimize-prompt.py utility. This allows external data to influence the final prompt sent to an LLM.\n
  • Ingestion points: TestCase.input in scripts/optimize-prompt.py and the render methods in references/prompt-templates.md.\n
  • Boundary markers: None are implemented to separate instructions from user-provided data.\n
  • Capability inventory: The skill performs local JSON file writing and interacts with LLM APIs; it does not execute system commands or perform unauthorized network operations.\n
  • Sanitization: No sanitization or escaping of user-provided variables is performed before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 07:17 AM