require-llm-output-encoding

Require encoding of LLM outputs based on usage context.

OWASP LLM Top 10 2025: LLM05 - Improper Output Handling
CWE: CWE-116
Severity: 🔴 Critical

Rule Details

Enforces proper encoding of LLM outputs before use in HTML, SQL, or other contexts.

❌ Incorrect

element.innerHTML = llmOutput;
db.query(`SELECT * FROM users WHERE name = '${llmOutput}'`);

✅ Correct

const safe = escapeHTML(llmOutput);
element.innerHTML = safe;

db.query('SELECT * FROM users WHERE name = ?', [llmOutput]);

Options

{
  "secure-coding/require-llm-output-encoding": ["error"]
}

Best Practices

• HTML: Use escapeHTML() or set textContent instead of innerHTML
• SQL: Use parameterized queries
• Shell: Avoid if possible, or use proper escaping

Version

Introduced in v2.3.0

Known False Negatives

The following patterns are not detected due to static analysis limitations:

Prompt from Variable

Why: Prompt content from variables not traced.

// ❌ NOT DETECTED - Prompt from variable
const prompt = buildPrompt(userInput);
await generateText({ prompt });

Mitigation: Validate all prompt components.

Nested Context

Why: Deep nesting obscures injection.

// ❌ NOT DETECTED - Nested
const messages = [{ role: 'user', content: userInput }];
await chat({ messages });

Mitigation: Validate at all levels.

Custom AI Wrappers

Why: Custom AI clients not recognized.

// ❌ NOT DETECTED - Custom wrapper
myAI.complete(userPrompt);

Mitigation: Apply rule to wrapper implementations.