vetkit.llm-app.request-input-in-system-prompt
Request input is interpolated into the system prompt. Text placed in the system role carries the developer's authority, so a user can rewrite the model's instructions (prompt injection) instead of merely asking it a question.
Last updated:
Suite: AI code risks
javascript, typescript
Request input is interpolated into the system prompt. Text placed in the system role carries the developer's authority, so a user can rewrite the model's instructions (prompt injection) instead of merely asking it a question.
Category: LLM SECURITY · Engine rule severity: WARNING
How to fix it
Keep the system prompt constant (or built only from trusted server-side values) and pass user-supplied text as a separate user message. If a user value must appear in the instructions, restrict it to an allow-listed enum.
References
Source: packages/engine/rules/llm-app/javascript.yml.
python
Request input is interpolated into the system prompt. Text placed in the system role carries the developer's authority, so a user can rewrite the model's instructions (prompt injection) instead of merely asking it a question.
Category: LLM SECURITY · Engine rule severity: WARNING
How to fix it
Keep the system prompt constant (or built only from trusted server-side values) and pass user-supplied text as a separate user message. If a user value must appear in the instructions, restrict it to an allow-listed enum.
References
Source: packages/engine/rules/llm-app/python.yml.
Generated from shipped rule definitions at build time. Matching is a review signal, not proof of exploitability. “generic” denotes text matching, not complete language or framework coverage. Runtime configuration and available tools affect whether a rule runs.