Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add bhuvangupta/vapt-claude --skill vapt-injectgit clone --depth 1 https://github.com/bhuvangupta/vapt-claudeWrote 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/bhuvangupta/vapt-claude/vapt-inject)<a href="https://agentmods.dev/skills/bhuvangupta/vapt-claude/vapt-inject"><img src="https://agentmods.dev/badge/skills/bhuvangupta/vapt-claude/vapt-inject/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/bhuvangupta/vapt-claude/vapt-inject"><img src="https://agentmods.dev/badge/skills/bhuvangupta/vapt-claude/vapt-inject.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.02022 |
| Opus 5 | $0.00000 | $0.01011 |
| Sonnet 5 | $0.00000 | $0.00404 |
| Haiku 4.5 | $0.00000 | $0.00202 |
Grade A, and why
vapt-inject scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL <url> | grep -oP 'href="[^"]*"' | sed 's/href="//;s/"//' | sort -u How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Injection Testing
When Invoked
The user runs /vapt inject <url> or this skill is triggered as part of Wave 3 during /vapt audit.
Prerequisites
Check for existing context:
- If
VAPT-WAVE2-CONTEXT.mdexists -> use discovered endpoints and parameters - If
VAPT-SCAN.mdexists -> extract parameter-accepting URLs - If no context -> run minimal endpoint discovery (crawl homepage links, check robots.txt)
Phase 1: Parameter Discovery
1.1 Endpoint Crawling
# Extract links from homepage
curl -sL <url> | grep -oP 'href="[^"]*"' | sed 's/href="//;s/"//' | sort -u
# Extract form actions and input names
curl -sL <url> | grep -oP '<form[^>]*action="[^"]*"'
curl -sL <url> | grep -oP '<input[^>]*name="[^"]*"'
1.2 Parameter Identification
If arjun is installed:
arjun -u <url> -m GET,POST
Fallback: Extract parameters from:
- URL query strings
- Form fields (GET and POST)
- JSON request bodies (from API endpoints)
- HTTP headers (Host, Referer, X-Forwarded-For)
- Cookie values
Compile a target list: [{url, method, parameter, location}]
Phase 2: SQL Injection Testing
2.1 Detection
If sqlmap is installed:
# Test a single URL with parameters
sqlmap -u "<url>?param=value" --batch --level 3 --risk 2 --threads 4
# For POST data
sqlmap -u "<url>" --data "param=value" --batch --level 3 --risk 2
Pro mode uses higher levels:
sqlmap -u "<url>?param=value" --batch --level 5 --risk 3 --threads 10 --tamper=space2comment
Fallback (curl-based detection):
Test each parameter with these payloads and compare responses:
- Single quote
'(error-based detection) - Boolean conditions:
OR 1=1vsOR 1=2 - Time delays:
SLEEP(3)orWAITFOR DELAY - UNION probes:
UNION SELECT NULL
Compare response length and time to baseline. Significant differences indicate potential injection.
2.2 Confirmation
If a potential SQLi is detected:
- Verify with a true/false comparison
- Confirm the DBMS type if possible
- Do NOT extract sensitive data -- just prove the vulnerability exists
- Record the payload, injection point, and evidence
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 · 271 lines · 0 tokens per session scan A fdb99593ad42
vapt-inject is a skill published in the GitHub repository bhuvangupta/vapt-claude (1 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,022 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
verification-loop
This skill should be used when the user asks to "verify code", "run verification", "check quality", "validate changes", or before creating a PR. Provides comprehensive verification including build, type check, lint, tests, security scan, and diff review.
test-native-extension
Validate a third-party control repo across four automated layers plus one printed manual recipe. Layer 1 asserts native-source structure (Android getName() and iOS +moduleName to manifest nativeModule; @ReactMethod / RCTEXPORTMETHOD to methods; no @ReactModule) plus load/init readiness (ReactPackage public no-arg…
test-site
Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.
performing-soap-web-service-security-testing
Perform security testing of SOAP web services by analyzing WSDL definitions and testing for XML injection, XXE, WS-Security bypass, and SOAPAction spoofing.
race
Race condition / TOCTOU playbook — limit overrun (one-time codes used twice, gift cards spent twice), single-packet attack (last-byte sync) to force parallel processing, and state-confusion races (file upload + read, order before payment). Use when timing-sensitive logic could be abused — one-time codes, coupons/gift…
ln-41-test-strategy-planner
Plans a risk-based test portfolio and prioritized scenarios without editing tests. Not for test execution or implementation.