Custom AI Agent is a Burp Suite extension that adds AI-assisted security analysis, scanning, and connections to external AI agents through MCP. It is intended for security testers and bug bounty researchers using local or cloud AI providers during manual and automated web-application testing.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/six2dez/burp-ai-agentnpx agentmods add skills/six2dez/burp-ai-agent/burp-scanWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/six2dez/burp-ai-agent/burp-scan)<a href="https://agentmods.dev/skills/six2dez/burp-ai-agent/burp-scan"><img src="https://agentmods.dev/badge/skills/six2dez/burp-ai-agent/burp-scan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/six2dez/burp-ai-agent/burp-scan"><img src="https://agentmods.dev/badge/skills/six2dez/burp-ai-agent/burp-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 13 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 126 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- high Privilege Escalation · line 244 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 245 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 248 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 249 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 251 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 252 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 300 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 308 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Server-Side Request Forgery · line 298 Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
- high Server-Side Request Forgery · line 299 Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
- high Data Exfiltration · line 427 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- high YARA Match · line 464 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.06735 |
| Opus 5 | $0.00044 | $0.03367 |
| Sonnet 5 | $0.00017 | $0.01347 |
| Haiku 4.5 | $0.00009 | $0.00673 |
Grade C, and why
burp-scan scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Cloud metadata endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
http://169.254.169.254/latest/meta-data/ (AWS metadata) [MODERATE] Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
fetch("url"), axios.METHOD("url"), $.ajax({url:"..."}), XMLHttpRequest.open("METHOD","url") How it starts
The opening of the file, as written. The whole thing — 647 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Burp Scan Skill
Tactical scanning engine for Burp Suite via MCP. Operates Burp's tools programmatically to discover, confirm, and report vulnerabilities.
Prerequisites: Burp Suite running with the AI Agent extension loaded and MCP server enabled.
1. MCP TOOL REFERENCE
Tools organized by scanning action. Tools marked [unsafe] require Unsafe Mode enabled. Tools marked [pro] require Burp Professional.
Discover Scope & Attack Surface
| Tool | Purpose |
|---|---|
scope_check |
Check if a URL is in scope |
site_map |
Browse Burp's site map |
site_map_regex |
Search site map by regex |
proxy_http_history |
List proxy HTTP history items |
proxy_http_history_regex |
Search proxy history by regex |
proxy_ws_history |
List WebSocket history |
proxy_ws_history_regex |
Search WebSocket history by regex |
response_body_search |
Regex search across all response bodies |
Analyze Traffic
| Tool | Purpose |
|---|---|
params_extract |
Extract parameters from a request |
find_reflected |
Find reflected parameter values in a response |
insertion_points |
List insertion point offsets for a request |
request_parse |
Parse raw HTTP request into structured fields |
response_parse |
Parse raw HTTP response into structured fields |
diff_requests |
Line diff between two requests |
Send Test Payloads
| Tool | Purpose |
|---|---|
http1_request [unsafe] |
Send HTTP/1.1 request through Burp and get response |
http2_request [unsafe] |
Send HTTP/2 request through Burp and get response |
repeater_tab [unsafe] |
Create a Repeater tab with a request |
repeater_tab_with_payload [unsafe] |
Create Repeater tab with placeholder replacement |
intruder [unsafe] |
Send request to Intruder |
intruder_prepare [unsafe] |
Create Intruder tab with explicit insertion points |
Out-of-Band (OOB) Verification
| Tool | Purpose |
|---|---|
collaborator_generate |
Generate a Burp Collaborator payload (unique subdomain) |
collaborator_poll |
Poll for Collaborator interactions (DNS/HTTP callbacks) |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 647 lines · 87 tokens per session scan C 26803bdd77ee
burp-scan is a skill published in the GitHub repository six2dez/burp-ai-agent (1,491 stars, last pushed 7d ago), licensed MIT. It adds 87 tokens to every session and 6,735 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
osmedeus-expert
Expert guide for the Osmedeus security automation workflow engine. Use when: (1) writing or editing YAML workflows (modules and flows), (2) running osmedeus CLI commands (scan, workflow management, installation, server), (3) configuring steps, runners, triggers, or template variables, (4) debugging workflow execution…
XSS_SKILL
Cross-site scripting skill vision validation.
jsrip-scan
Use when user asks to scan a target for exposed JavaScript secrets, run a jsrip scan, analyze findings for true/false positives, or says /jsrip-scan. Single-target bug bounty recon — runs jsrip then auto-classifies every finding.
dsl-vm-reverse
A specialized guide for analyzing a custom virtual machine written in JavaScript, including its instruction codes and runtime behavior. A virtual machine here is a program that interprets its own small instruction language.
apk-reverse
A command-line workflow for analysing Android APK files, which are installable Android application packages. It covers reading app code and configuration, changing low-level code, rebuilding the package, and observing the app while it runs.
src-hunter
A guided workflow for authorized security testing and bug-bounty research. It covers finding, checking, and reporting common web and application vulnerabilities.