system-prompt
Refine DBX Studio AI Prompts
DBX Studio needs consistent assistant behavior across streaming and tool providers. This skill guides prompt edits for tone, tool order, response format, and SQL safety.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "system-prompt" from https://skillstore.io/skills/dbxstudio-system-prompt.md and its manifest at https://skillstore.io/api/skills/dbxstudio-system-prompt/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "system-prompt". Make DBX Studio answers shorter but keep the results clear.
Expected outcome:
The skill identifies both prompt locations, proposes concise response rules, keeps result-first behavior, and notes files that need edits.
Using "system-prompt". Ensure charts are recommended only when useful.
Expected outcome:
The skill points to chart guidance in the unified prompt structure and suggests clearer chart selection rules for line, bar, pie, scatter, and histogram output.
Using "system-prompt". Align Claude and OpenAI tool prompts.
Expected outcome:
The skill compares the streaming and oRPC prompt sections and recommends synchronized tool order, examples, and schema context wording.
Security Audit
SafeAll static command-execution findings are Markdown code formatting or inline code references, not executable shell syntax. The traversal findings are hardcoded Markdown links to project files, with no dynamic path construction or untrusted input. No semantic prompt injection, data exfiltration, or hidden behavior was found in SKILL.md.
Risk Factors
โ๏ธ External commands (12)
๐ Filesystem access (2)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/dbxstudio-system-prompt/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/dbxstudio-system-prompt?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/dbxstudio-system-prompt?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/dbxstudio-system-prompt/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/dbxstudio-system-prompt.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA ยท BibTeX ยท CFF)
APA citation
Dbxstudio. (2026). system-prompt security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/dbxstudio-system-prompt/audits/4BibTeX citation
@techreport{dbxstudio-dbxstudio-system-prompt-2026,
author = {Dbxstudio},
title = {system-prompt security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/dbxstudio-system-prompt/audits/4},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "system-prompt security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "Dbxstudio"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/dbxstudio-system-prompt/audits/4"
identifiers:
- type: other
value: "skillstore:dbxstudio-system-prompt:audit:4"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Update Chat Behavior
Change DBX Studio assistant tone, response length, or result order while preserving existing prompt structure.
Standardize Tool Use
Align streaming and oRPC provider prompts so both assistants follow the same tool order and response rules.
Review Prompt Consistency
Check prompt edits against documented schema context, SQL formatting, examples, and query safety expectations.
Try These Prompts
Use the system-prompt skill to identify where DBX Studio defines its AI chat system prompts. Summarize each location and explain when it runs.
Use the system-prompt skill to make DBX Studio replies more concise while keeping results first and SQL formatting rules intact.
Use the system-prompt skill to compare the streaming and oRPC prompt guidance. Update them so tool order, examples, and response rules match.
Use the system-prompt skill to redesign the DBX Studio assistant prompt for schema-aware analysis, safe query generation, chart selection, and provider consistency. Preserve live schema context and document the changes.
Best Practices
- Review both prompt locations before editing so provider behavior stays consistent.
- Keep schema context placeholders intact unless the application code changes with them.
- Test prompts with realistic database questions after each change.
Avoid
- Editing only one provider prompt and leaving the other with conflicting rules.
- Removing schema or query context placeholders without replacing their runtime purpose.
- Adding broad assistant behavior rules that weaken SQL safety or tool ordering.