- Home
- Skills
- Agents & Orchestration
- eight reviewer prompt audit
eight reviewer prompt audit
Professional prompt auditing skill that stress-tests LLM instructions across 8 axes with scored verdicts and diffs.
$5
Works with the AI Agents you already use
eight reviewer prompt audit
Example session with this skill installed
Audit the system prompt in src/agents/researcher.txt. Check for injection risks and output contract stability. Use the default rubrics.
- Read your context and instructions
- Compiled the eight reviewer prompt
Verdict: FAIL (Critical Injection Safety)
Scores: Safety: 2/10, Contract: 7/10, Total: 42/100.
Findings
- [Safety] Critical: Untrusted user queries are not delimited.
- Fix: Wrap {{user_input}} in <user_query> tags.
- [Contract] Minor: Missing 'null' case for JSON field 'references'.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
LLM prompts often fail silently in production due to hidden vulnerabilities like prompt injection, hallucination triggers, or fragile output schemas. Developers typically rely on "vibe-based" testing, which misses critical edge cases and results in unstable agent behavior.
What it does
- Performs an 8-point audit covering framing, safety, robustness, and cost.
- Identifies prompt injection vectors and privilege separation gaps.
- Scores prompts using a weighted rubric to provide a quantitative quality verdict.
- Generates specific diffs or rewrites for every identified weakness.
- Enforces strict gating rules for security and grounding criticals.
Frameworks & tools
Works with any LLM instruction set, including system prompts, agent personas, and tool-use instructions. Supports JSON schema validation for output contracts.
Why this beats prompting it yourself
Manual review is subjective and inconsistent. This skill applies a systematic, disjoint rubric that forces the auditor to evaluate safety and robustness independently of clarity, ensuring no axis is overlooked. It replaces guesswork with a repeatable, scored process that includes immediate code-level fixes.
Use cases
- Hardening an agent against prompt injection before deployment.
- Reducing token costs by identifying redundant instructions.
- Ensuring consistent JSON output for downstream parsers.
- Stress-testing prompts against adversarial inputs and edge cases.
Known limitations
Requires access to internal rubric and schema files to execute the full scoring logic. Injection safety analysis is most accurate when the runtime context and tool definitions are provided.
Requires references/rubrics.md and references/schema.json to be available in the workspace. Effectiveness on injection safety depends on providing runtime context.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 months ago
Permissions
No special permissions declared or detected