CalvinBackup/shannon
1
0
Fork 0
mirror of https://github.com/KeygraphHQ/shannon.git synced 2026-04-01 10:20:53 +02:00
Code Issues Packages Projects Releases Wiki Activity

chore: update pipeline testing vulnerability prompts

Browse Source
This commit is contained in:
ezl-keygraph
2026-03-03 02:05:09 +05:30
parent b62abfea4c
commit 3ec491b30b
5 changed files with 50 additions and 170 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
prompts/pipeline-testing/vuln-auth.txt
View File

@@ -1,37 +1,13 @@
## 🧪 Pipeline Testing: MCP Isolation Test for Auth Agent
Please complete these tasks using your MCP tools:
**MCP Server Assignment:** Using `{{MCP_SERVER}}` for browser automation testing.
1. Navigate to https://example.net and take a screenshot:
- Use {{MCP_SERVER}}__browser_navigate to go to https://example.net
- Use {{MCP_SERVER}}__browser_take_screenshot
### Step 1: Test Browser Isolation
1. Navigate to the test site using your assigned MCP server:
```
{{MCP_SERVER}}__browser_navigate to https://example.net
```
2. Save an analysis deliverable:
- Use save_deliverable with deliverable_type "AUTH_ANALYSIS"
- Content: "# Auth Analysis Report\n\nAnalysis complete. No authentication vulnerabilities identified."
2. Take a screenshot to prove isolation:
```
{{MCP_SERVER}}__browser_take_screenshot with filename "auth-agent-test.png"
```
3. Log the test results:
```
console.log("🔵 AUTH AGENT - MCP Server: {{MCP_SERVER}} - Successfully navigated to example.net")
```
### Step 2: Create Required Deliverables
Use the save_deliverable MCP tool to create both deliverables:
**1. Analysis Report:**
Use `save_deliverable` MCP tool with:
- `deliverable_type: "AUTH_ANALYSIS"`
- `content: "# Auth Analysis Complete (Pipeline Test)\n\n**MCP Server Used:** {{MCP_SERVER}}\n**Test Site:** https://example.net\n**Screenshot:** auth-agent-test.png\n**Status:** Browser isolation test successful"`
**2. Exploitation Queue:**
Use `save_deliverable` MCP tool with:
- `deliverable_type: "AUTH_QUEUE"`
- `content: {"vulnerabilities": [{"ID": "AUTH-VULN-01", "verdict": "vulnerable", "confidence": "high", "notes": "Test auth vulnerability for pipeline validation (MCP: {{MCP_SERVER}})", "vulnerability_type": "Authentication_Bypass", "endpoint": "/api/login", "flaw_type": "Missing token validation", "exploit_hypothesis": "Empty or invalid token allows access to protected resources", "witness_payload": "Authorization: Bearer invalid_token"}]}`
These tools will automatically create the correct files in `deliverables/`.
### Step 3: Verify MCP Isolation
This agent should be using {{MCP_SERVER}} and navigating to example.net independently of other parallel agents.
3. Save a queue deliverable:
- Use save_deliverable with deliverable_type "AUTH_QUEUE"
- Content: {"vulnerabilities": []}

44
prompts/pipeline-testing/vuln-authz.txt
View File

@@ -1,37 +1,13 @@
## 🧪 Pipeline Testing: MCP Isolation Test for Authorization Agent
Please complete these tasks using your MCP tools:
**MCP Server Assignment:** Using `{{MCP_SERVER}}` for browser automation testing.
1. Navigate to https://jsonplaceholder.typicode.com and take a screenshot:
- Use {{MCP_SERVER}}__browser_navigate to go to https://jsonplaceholder.typicode.com
- Use {{MCP_SERVER}}__browser_take_screenshot
### Step 1: Test Browser Isolation
1. Navigate to the test site using your assigned MCP server:
```
{{MCP_SERVER}}__browser_navigate to https://jsonplaceholder.typicode.com
```
2. Save an analysis deliverable:
- Use save_deliverable with deliverable_type "AUTHZ_ANALYSIS"
- Content: "# Authorization Analysis Report\n\nAnalysis complete. No authorization vulnerabilities identified."
2. Take a screenshot to prove isolation:
```
{{MCP_SERVER}}__browser_take_screenshot with filename "authz-agent-test.png"
```
3. Log the test results:
```
console.log("🟢 AUTHZ AGENT - MCP Server: {{MCP_SERVER}} - Successfully navigated to jsonplaceholder.typicode.com")
```
### Step 2: Create Required Deliverables
Use the save_deliverable MCP tool to create both deliverables:
**1. Analysis Report:**
Use `save_deliverable` MCP tool with:
- `deliverable_type: "AUTHZ_ANALYSIS"`
- `content: "# Authorization Analysis Complete (Pipeline Test)\n\n**MCP Server Used:** {{MCP_SERVER}}\n**Test Site:** https://jsonplaceholder.typicode.com\n**Screenshot:** authz-agent-test.png\n**Status:** Browser isolation test successful"`
**2. Exploitation Queue:**
Use `save_deliverable` MCP tool with:
- `deliverable_type: "AUTHZ_QUEUE"`
- `content: {"vulnerabilities": [{"ID": "AUTHZ-VULN-01", "verdict": "vulnerable", "confidence": "high", "notes": "Test authz vulnerability for pipeline validation (MCP: {{MCP_SERVER}})", "vulnerability_type": "Vertical", "endpoint": "/admin/users", "actual_access": "Regular users can access admin functions", "witness_payload": "GET /admin/users with regular user token"}]}`
These tools will automatically create the correct files in `deliverables/`.
### Step 3: Verify MCP Isolation
This agent should be using {{MCP_SERVER}} and navigating to jsonplaceholder.typicode.com independently of other parallel agents.
3. Save a queue deliverable:
- Use save_deliverable with deliverable_type "AUTHZ_QUEUE"
- Content: {"vulnerabilities": []}

44
prompts/pipeline-testing/vuln-injection.txt
View File

@@ -1,37 +1,13 @@
## 🧪 Pipeline Testing: MCP Isolation Test for Injection Agent
Please complete these tasks using your MCP tools:
**MCP Server Assignment:** Using `{{MCP_SERVER}}` for browser automation testing.
1. Navigate to https://example.com and take a screenshot:
- Use {{MCP_SERVER}}__browser_navigate to go to https://example.com
- Use {{MCP_SERVER}}__browser_take_screenshot
### Step 1: Test Browser Isolation
1. Navigate to the test site using your assigned MCP server:
```
{{MCP_SERVER}}__browser_navigate to https://example.com
```
2. Save an analysis deliverable:
- Use save_deliverable with deliverable_type "INJECTION_ANALYSIS"
- Content: "# Injection Analysis Report\n\nAnalysis complete. No injection vulnerabilities identified."
2. Take a screenshot to prove isolation:
```
{{MCP_SERVER}}__browser_take_screenshot with filename "injection-agent-test.png"
```
3. Log the test results:
```
console.log("🔴 INJECTION AGENT - MCP Server: {{MCP_SERVER}} - Successfully navigated to example.com")
```
### Step 2: Create Required Deliverables
Use the save_deliverable MCP tool to create both deliverables:
**1. Analysis Report:**
Use `save_deliverable` MCP tool with:
- `deliverable_type: "INJECTION_ANALYSIS"`
- `content: "# Injection Analysis Complete (Pipeline Test)\n\n**MCP Server Used:** {{MCP_SERVER}}\n**Test Site:** https://example.com\n**Screenshot:** injection-agent-test.png\n**Status:** Browser isolation test successful"`
**2. Exploitation Queue:**
Use `save_deliverable` MCP tool with:
- `deliverable_type: "INJECTION_QUEUE"`
- `content: {"vulnerabilities": [{"ID": "INJ-VULN-01", "verdict": "vulnerable", "confidence": "high", "notes": "Test vulnerability for pipeline validation (MCP: {{MCP_SERVER}})", "vulnerability_type": "SQLi", "source": "query parameter at app.js:15", "path": "controller → db.query", "sink_call": "db.query at app.js:20", "slot_type": "SQL-val", "mismatch_reason": "User input directly concatenated into SQL query", "witness_payload": "'; DROP TABLE users; --"}]}`
These tools will automatically create the correct files in `deliverables/`.
### Step 3: Verify MCP Isolation
This agent should be using {{MCP_SERVER}} and navigating to example.com independently of other parallel agents.
3. Save a queue deliverable:
- Use save_deliverable with deliverable_type "INJECTION_QUEUE"
- Content: {"vulnerabilities": []}

44
prompts/pipeline-testing/vuln-ssrf.txt
View File

@@ -1,37 +1,13 @@
## 🧪 Pipeline Testing: MCP Isolation Test for SSRF Agent
Please complete these tasks using your MCP tools:
**MCP Server Assignment:** Using `{{MCP_SERVER}}` for browser automation testing.
1. Navigate to https://httpbin.org and take a screenshot:
- Use {{MCP_SERVER}}__browser_navigate to go to https://httpbin.org
- Use {{MCP_SERVER}}__browser_take_screenshot
### Step 1: Test Browser Isolation
1. Navigate to the test site using your assigned MCP server:
```
{{MCP_SERVER}}__browser_navigate to https://httpbin.org
```
2. Save an analysis deliverable:
- Use save_deliverable with deliverable_type "SSRF_ANALYSIS"
- Content: "# SSRF Analysis Report\n\nAnalysis complete. No SSRF vulnerabilities identified."
2. Take a screenshot to prove isolation:
```
{{MCP_SERVER}}__browser_take_screenshot with filename "ssrf-agent-test.png"
```
3. Log the test results:
```
console.log("🟠 SSRF AGENT - MCP Server: {{MCP_SERVER}} - Successfully navigated to httpbin.org")
```
### Step 2: Create Required Deliverables
Use the save_deliverable MCP tool to create both deliverables:
**1. Analysis Report:**
Use `save_deliverable` MCP tool with:
- `deliverable_type: "SSRF_ANALYSIS"`
- `content: "# SSRF Analysis Complete (Pipeline Test)\n\n**MCP Server Used:** {{MCP_SERVER}}\n**Test Site:** https://httpbin.org\n**Screenshot:** ssrf-agent-test.png\n**Status:** Browser isolation test successful"`
**2. Exploitation Queue:**
Use `save_deliverable` MCP tool with:
- `deliverable_type: "SSRF_QUEUE"`
- `content: {"vulnerabilities": [{"ID": "SSRF-VULN-01", "verdict": "vulnerable", "confidence": "high", "notes": "Test SSRF vulnerability for pipeline validation (MCP: {{MCP_SERVER}})", "vulnerability_type": "URL_Manipulation", "source": "url parameter in /api/fetch", "outbound_call": "fetch() at api.js:45", "witness_payload": "http://internal.localhost/admin"}]}`
These tools will automatically create the correct files in `deliverables/`.
### Step 3: Verify MCP Isolation
This agent should be using {{MCP_SERVER}} and navigating to httpbin.org independently of other parallel agents.
3. Save a queue deliverable:
- Use save_deliverable with deliverable_type "SSRF_QUEUE"
- Content: {"vulnerabilities": []}

44
prompts/pipeline-testing/vuln-xss.txt
View File

@@ -1,37 +1,13 @@
## 🧪 Pipeline Testing: MCP Isolation Test for XSS Agent
Please complete these tasks using your MCP tools:
**MCP Server Assignment:** Using `{{MCP_SERVER}}` for browser automation testing.
1. Navigate to https://example.org and take a screenshot:
- Use {{MCP_SERVER}}__browser_navigate to go to https://example.org
- Use {{MCP_SERVER}}__browser_take_screenshot
### Step 1: Test Browser Isolation
1. Navigate to the test site using your assigned MCP server:
```
{{MCP_SERVER}}__browser_navigate to https://example.org
```
2. Save an analysis deliverable:
- Use save_deliverable with deliverable_type "XSS_ANALYSIS"
- Content: "# XSS Analysis Report\n\nAnalysis complete. No XSS vulnerabilities identified."
2. Take a screenshot to prove isolation:
```
{{MCP_SERVER}}__browser_take_screenshot with filename "xss-agent-test.png"
```
3. Log the test results:
```
console.log("🟡 XSS AGENT - MCP Server: {{MCP_SERVER}} - Successfully navigated to example.org")
```
### Step 2: Create Required Deliverables
Use the save_deliverable MCP tool to create both deliverables:
**1. Analysis Report:**
Use `save_deliverable` MCP tool with:
- `deliverable_type: "XSS_ANALYSIS"`
- `content: "# XSS Analysis Complete (Pipeline Test)\n\n**MCP Server Used:** {{MCP_SERVER}}\n**Test Site:** https://example.org\n**Screenshot:** xss-agent-test.png\n**Status:** Browser isolation test successful"`
**2. Exploitation Queue:**
Use `save_deliverable` MCP tool with:
- `deliverable_type: "XSS_QUEUE"`
- `content: {"vulnerabilities": [{"ID": "XSS-VULN-01", "verdict": "vulnerable", "confidence": "high", "notes": "Test XSS vulnerability for pipeline validation (MCP: {{MCP_SERVER}})", "vulnerability_type": "Reflected", "source": "search parameter", "sink_function": "template.render at search.js:25", "render_context": "HTML_BODY", "mismatch_reason": "User input rendered without HTML encoding", "witness_payload": "<script>alert(1)</script>"}]}`
These tools will automatically create the correct files in `deliverables/`.
### Step 3: Verify MCP Isolation
This agent should be using {{MCP_SERVER}} and navigating to example.org independently of other parallel agents.
3. Save a queue deliverable:
- Use save_deliverable with deliverable_type "XSS_QUEUE"
- Content: {"vulnerabilities": []}