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 latestaiagents/agent-skills --skill injection-preventiongit clone --depth 1 https://github.com/latestaiagents/agent-skillsWrote 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/latestaiagents/agent-skills/injection-prevention)<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/injection-prevention"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/injection-prevention/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/latestaiagents/agent-skills/injection-prevention"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/injection-prevention.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 | $0.00078 | $0.01746 |
| Opus 5 | $0.00039 | $0.00873 |
| Sonnet 5 | $0.00016 | $0.00349 |
| Haiku 4.5 | $0.00008 | $0.00175 |
Grade A, and why
injection-prevention scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| Command Injection | CRITICAL | Shell exec, system calls, child_process | How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Injection Prevention (OWASP A01)
Prevent SQL, NoSQL, Command, and other injection attacks by validating and sanitizing all user input.
When to Use
- Reviewing code that builds SQL/NoSQL queries
- Code that executes shell commands
- Any place user input reaches an interpreter
- Building APIs that accept user data
- Migrating from string concatenation to parameterized queries
Injection Types
| Type | Danger | Common Locations |
|---|---|---|
| SQL Injection | CRITICAL | Database queries, ORMs with raw queries |
| NoSQL Injection | CRITICAL | MongoDB, Redis, Elasticsearch queries |
| Command Injection | CRITICAL | Shell exec, system calls, child_process |
| LDAP Injection | HIGH | Directory service queries |
| XPath Injection | HIGH | XML document queries |
| Expression Language | HIGH | Template engines, eval() |
Detection Patterns
SQL Injection Red Flags
// VULNERABLE - String concatenation
const query = "SELECT * FROM users WHERE id = " + userId;
const query = `SELECT * FROM users WHERE name = '${userName}'`;
// VULNERABLE - Format strings
query = "SELECT * FROM users WHERE id = %s" % user_id
// VULNERABLE - String interpolation in ORM
User.where("name = '#{params[:name]}'")
Command Injection Red Flags
// VULNERABLE - Direct user input in commands
exec(`ls ${userInput}`);
system("ping " + ipAddress);
child_process.exec(`convert ${filename} output.png`);
// VULNERABLE - eval with user data
eval(userCode);
new Function(userInput)();
Prevention Techniques
1. Parameterized Queries (SQL)
// SAFE - Node.js with parameterized query
const result = await db.query(
'SELECT * FROM users WHERE id = $1 AND status = $2',
[userId, status]
);
// SAFE - Using ORM properly
const user = await User.findOne({ where: { id: userId } });
// SAFE - Prepared statements
const stmt = db.prepare('SELECT * FROM users WHERE email = ?');
const user = stmt.get(email);
# SAFE - Python with parameterized query
cursor.execute(
"SELECT * FROM users WHERE id = %s AND status = %s",
(user_id, status)
)
# SAFE - SQLAlchemy ORM
user = session.query(User).filter(User.id == user_id).first()
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 · 265 lines · 78 tokens per session scan A 73816b5d5550
injection-prevention is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 1,746 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ai-critique
A general diagnosis assistant for product, operations, technical, and software work. It analyzes supplied material and produces a summary, conclusions, action suggestions, and reusable deliverables.
ai-equipment-failure-rca-draft
A root-cause analysis draft assistant for investigating equipment failures. Root-cause analysis means looking for the underlying reason a failure happened, not only its visible symptom.
ai-performance
A performance diagnosis assistant for finding what may be slowing a service or product down.
ai-quality-complaint-8d-report
A business-diagnosis assistant for creating or reviewing an 8D report. An 8D report is a structured method for investigating a quality problem and documenting corrective action.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
moai-workflow-loop
Ralph Engine - Automated feedback loop with LSP diagnostics and AST-grep integration for continuous code quality improvement. Use when implementing error-driven development, automated fixing, or continuous quality validation workflows.