New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Webvuln

by PentesterFlow in PentesterFlow/agent

Web vulnerability hunting playbook. An agent skill from PentesterFlow/agent.

Apache-2.0Auto-check passedSecurity

Install Webvuln

skills CLI
$ npx skills add PentesterFlow/agent --skill webvuln -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install PentesterFlow/agent webvuln --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/PentesterFlow/agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/webvuln .claude/skills/webvuln && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
webvuln
GitHub stars
1.4k
Token cost
~1.2k tokens
SKILL.md length
501 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Web vulnerability hunting playbook. An agent skill from PentesterFlow/agent.

  • Works in 6 steps: Triage the target → Known-CVE pass (manual, curl-driven) → Auth + access control (IDOR / BAC) → …
  • Tasks that involve Web application vulnerabilities
  • SKILL.md covers 1. Triage the target, 2. Known-CVE pass (manual,…, 3. Auth + access control (IDOR… and 4. Injection surfaces…, plus 2 more sections
  • Calls curl and jq

What it does

Webvuln is an agent skill from PentesterFlow/agent. Web vulnerability hunting playbook. Use after recon, when you have specific hosts/endpoints to test for IDOR/BAC, injection, auth flaws, SSRF, and known CVEs. Emphasizes real PoC + concrete impact.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Security, covering Web application vulnerabilities and Vulnerability scanning. The repository describes itself as: Agentic offensive-security in your terminal. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Web application vulnerabilities
  • Tasks that involve Vulnerability scanning

Example prompts

  • “/webvuln”

Requirements

  • Pre-approved tools (allowed-tools): shell, http, web_search, web_fetch, file_write

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Triage the target
  2. Known-CVE pass (manual, curl-driven)
  3. Auth + access control (IDOR / BAC)
  4. Injection surfaces (curl-first)
  5. SSRF & open redirects
  6. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 0759d87. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • shell
    • http
    • web_search
    • web_fetch
    • file_write

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl
    • jq

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Webvuln loads about 1.2k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 501 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from PentesterFlow/agent at commit 0759d87, republished under its Apache-2.0 licence (© PentesterFlow). 501 words, ~1,158 tokens.

Download SKILL.mdSave it as .claude/skills/webvuln/SKILL.md (or your agent's skills folder).
name
webvuln
description
Web vulnerability hunting playbook. Use after recon, when you have specific hosts/endpoints to test for IDOR/BAC, injection, auth flaws, SSRF, and known CVEs. Emphasizes real PoC + concrete impact.
allowed-tools
shell, http, web_search, web_fetch, file_write

Web vuln hunting playbook

You are testing specific endpoints the user has handed you (or that came out of the recon skill). Every finding must come with a real PoC and a concrete impact statement — no theoretical bugs.

Default to curl and the built-in http tool. Do not pull in heavy scanners (nuclei, sqlmap, ffuf, etc.) unless the user explicitly asks for them or you have manually confirmed a bug and need a scanner only to characterize the bug class.

Execution rule: substitute real target values before running commands. Never write literal placeholders such as <TARGET>, <vulnerable-path>, or <PoC body> to files. If a value is unknown, ask once or derive it from /target.

1. Triage the target

Fetch the landing page with the http tool or curl. Note:

  • Framework / language signals (cookies, headers, error pages)
  • Authentication scheme (cookie, Bearer, basic)
  • API style (REST / GraphQL / gRPC)
  • Anything that suggests a known CVE family (versioned banner, vendor product name)

If you spot a versioned product, immediately web_search "<product> <version> CVE" and web_fetch the top advisory. Reproduce the CVE manually with curl before reporting.

2. Known-CVE pass (manual, curl-driven)

For each suspected CVE pulled from the advisory, craft the curl that proves it — single request when possible:

TARGET="https://app.example.com" # replace with the scoped target before running
curl -ksS -X POST "$TARGET/vulnerable-path" \
  -H 'Content-Type: application/json' \
  -d '{"replace":"with-real-poc-body"}' \
  -w "\nHTTP %{http_code}  size=%{size_download}  time=%{time_total}\n"

If the advisory describes a recognizable pattern (template injection, deserialization, etc.) and the user has explicitly authorized broader scanning, then — and only then — reach for nuclei against the single host. Otherwise stay manual.

3. Auth + access control (IDOR / BAC)

  • Identify any numeric or UUID identifiers in the URL path or query (/api/users/12345, /orders/?id=...).
  • With user-provided session A, fetch a resource you own.
  • Swap the identifier to another user's value (or use a second session from the user) and replay with curl or the http tool.
  • A 200 with foreign data = IDOR. Capture the curl one-liner and the response excerpt into findings/idor-<endpoint>.txt.

Example IDOR sweep with two sessions:

TARGET="https://app.example.com" # replace with the scoped target before running
for id in $(seq 1 50); do
  body=$(curl -ksS -H "Cookie: $SESSION_B" "$TARGET/api/users/$id" | jq -r '.email // empty')
  [ -n "$body" ] && echo "$id $body"
done
Show full SKILL.md (189 more words)Show less

4. Injection surfaces (curl-first)

For each parameter (query, body, header, cookie):

  • Inject simple probes (', ", <x>, ${7*7}, {{7*7}}) with curl or the http tool.
  • 500s / reflected payloads / arithmetic evaluation → escalate to a targeted PoC.

Quick reflected-XSS probe with curl:

TARGET="https://app.example.com" # replace with the scoped target before running
for p in q s search query keyword; do
  curl -ksS "$TARGET/?$p=pf$(date +%s)<svg/onload=alert(1)>" \
    | grep -o "pf[0-9]*<svg.*alert(1)>" || true
done

For SQLi: only after curl-level manual confirmation (timing differences, error strings) and only with the user's explicit OK, escalate to sqlmap with --batch --level=2 --risk=1 --random-agent against the single endpoint. Default path is manual ' OR sleep(5) -- style probes via curl, then exfil via UNION when you know the schema.

5. SSRF & open redirects

Any parameter that takes a URL or hostname: try http://127.0.0.1, http://169.254.169.254/latest/meta-data/, and an out-of-band canary the user provides. Compare response timings and bodies with curl -w "%{time_total} %{size_download}\n".

6. Report

For each confirmed finding, write findings/<id>-<short-title>.md with:

  • Title, severity (VRT-aligned), category
  • Affected endpoint(s)
  • Step-by-step reproduction as the exact curl one-liner the reviewer can copy (with placeholders for session tokens)
  • Observed response excerpt proving the bug
  • Concrete impact (what data is exposed, what state can be changed, what privilege is escalated)
  • Suggested remediation

Stop after writing the report. Do not chain into further exploitation unless the user explicitly asks.

© PentesterFlow, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/webvuln of PentesterFlow/agent.

Open the folder on GitHubat commit 0759d87

Compare with similar skills

Webvuln next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Webvuln compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Webvuln this skillPentesterFlow/agent1.4k—~1.2kAutomated safety check: PassApache-2.0
Security Auditoreigent-ai/eigent15k—~1.8kAutomated safety check: NotesApache-2.0
Code Audit3stoneBrother/code-audit8931 repos~2.7kAutomated safety check: PassNone
Security Audit Scannerruvnet/ruflo74k2 repos~823Automated safety check: PassMIT
Octopus Security Auditnyldn/claude-octopus4.2k1 repos~2.3kAutomated safety check: PassMIT
Security Verification Gatefengshao1227/ccg-workflow5.9k—~621Automated safety check: NotesMIT

Similar skills

  • Security Auditor

    eigent-ai/eigent

    Audits source code, dependencies and config files for vulnerabilities and hardcoded secrets, using two bundled Python scanners and an OWASP Top 10 checklist.

    15k GitHub stars~1.8k tokensUpdated today
    SecurityAuto-check: notes

  • Code Audit

    3stoneBrother/code-audit

    Professional code security audit skill covering 55+ vulnerability types.

    893 GitHub starsUsed in 1 repo~2.7k tokens
    SecurityAuto-check passed

  • Security Audit Scanner

    ruvnet/ruflo

    Runs claude-flow CLI security scans for input validation, path traversal, SQL injection, XSS, hardcoded secrets and known CVEs, and writes an audit report.

    74k GitHub starsUsed in 2 repos~823 tokens
    SecurityAuto-check passed

  • Octopus Security Audit

    nyldn/claude-octopus

    OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews

    4.2k GitHub starsUsed in 1 repo~2.3k tokens
    SecurityAuto-check passed

  • Security Verification Gate

    fengshao1227/ccg-workflow

    Scans code with a bundled Node script for injection, secrets, XSS and other risky patterns, ranks findings by severity and checks that security decisions are documented.

    5.9k GitHub stars~621 tokensUpdated 22 days ago
    SecurityAuto-check: notes

  • Secknowledge Skill

    Pa55w0rd/secknowledge-skill

    Web+AI 安全测试知识库。融合 WooYun 88,636 案例 + 先知 L1-L4 方法论 + GAARM 173 风险 + OWASP Top 10 (LLM/ASI/WSTG)。

    423 GitHub stars~2.7k tokensUpdated 3 mo ago
    SecurityAuto-check passed

More from PentesterFlow/agent

  • Insecure Deserialization Playbook

    PentesterFlow/agent

    Fingerprints which language or framework produced a serialized blob, then helps build a working gadget chain to test for insecure deserialization.

    1.4k GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed

  • External Recon Playbook

    PentesterFlow/agent

    Maps the attack surface of a web domain you are authorized to test: confirms scope, lists subdomains from public sources, probes live hosts and fingerprints technology.

    1.4k GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Ssti

    PentesterFlow/agent

    Server-Side Template Injection — fingerprint the engine first (Jinja2 / Twig / Velocity / Freemarker / ERB / Smarty / Mako / Handlebars / Pug), then escalate the engine-specific primitive to RCE or…

    1.4k GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Takeover

    PentesterFlow/agent

    Subdomain takeover playbook — sweep subdomains for dangling CNAMEs / NS records pointing at unclaimed third-party resources (GitHub Pages, S3, Heroku, Azure, Netlify, Shopify, ...), confirm with the…

    1.4k GitHub stars~3.3k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Webvuln

What does Webvuln do?

Web vulnerability hunting playbook. An agent skill from PentesterFlow/agent. Webvuln is an agent skill from PentesterFlow/agent. Web vulnerability hunting playbook.

When should I use Webvuln?

Webvuln fits situations like: tasks that involve Web application vulnerabilities; tasks that involve Vulnerability scanning.

How do I install Webvuln in Claude Code?

Run `npx skills add PentesterFlow/agent --skill webvuln -a claude-code`. Or copy the skill folder (skills/webvuln in PentesterFlow/agent) into .claude/skills/webvuln in your project. Claude Code loads it when a task matches its description.

How do I install Webvuln in Codex?

Run `npx skills add PentesterFlow/agent --skill webvuln -a codex`. Or copy the skill folder (skills/webvuln in PentesterFlow/agent) into .agents/skills/webvuln in your project. Codex loads it when a task matches its description.

Can I use Webvuln in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add PentesterFlow/agent --skill webvuln -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/webvuln, .gemini/skills/webvuln, .github/skills/webvuln and .opencode/skills/webvuln in your project.

What does Webvuln need to run?

Going by SKILL.md and its folder, Webvuln needs the command-line tools its instructions call (curl and jq). Its frontmatter pre-approves these tools: shell, http, web_search, web_fetch, file_write.

Does Webvuln access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Webvuln safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Webvuln use?

Webvuln is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Webvuln use?

About 1.2k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Webvuln?

Skills that share tags, products or a category with Webvuln: Security Auditor (eigent-ai/eigent, 15k stars), Code Audit (3stoneBrother/code-audit, 893 stars), Security Audit Scanner (ruvnet/ruflo, 74k stars) and Octopus Security Audit (nyldn/claude-octopus, 4.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Webvuln?

PentesterFlow (a GitHub user) maintains it in PentesterFlow/agent, which has 1,391 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on August 31, 2026.

Source: PentesterFlow/agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.