prompt_injection_persona
Prompt injection attempt (persona)
Line 2969Snippets
if not re.search(r'you are|act as|as a\s+\w+', analysis.sections[0].get('content', [''])[0] if analysis.sections else '', re.IGNORECASE):hardcoded_secret
Potentially hardcoded secret
Potentially hardcoded secret
Line 1729Snippets
query = f"SELECT * FROM users WHERE username='{username}' AND password='{password}'" query = f"SELECT * FROM users WHERE username='{username}' AND password='{password}'"Trust Score
Updated semana passada
Analisado
31 de mar. de 2026, 15:57
+ 2 previous scans
Compatível com
Skill details
Updated semana passada
Analisado 31 de mar. de 2026, 15:57
Descricao
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RAG", "create few-shot examples", "analyze token usage", or "design AI workflows". Use for prompt engineering patterns, LLM evaluation frameworks, agent architectures, and str...
Scans recentes
31 de mar. de 2026, 15:57
Latest analysis
31 de mar. de 2026, 15:12
Run 2
27 de mar. de 2026, 15:47
Run 1