Skip to content
Fallow home
All docs pages

Docs home

Untrusted input reaches an LLM call

What a llm-call-injection finding of fallow security means, why it matters and how to fix it.

What it reports

Catalogue security candidate for CWE-1427.

Security explains how fallow finds it.

Why it matters

Input from the request goes into the prompt. An attacker can write instructions that change what the model does, for example to leak the system prompt or call tools.

Example

openai.chat.completions.create({ messages: [{ role: 'user', content: req.body.q }] });

Fix

Review the candidate trace before acting. Confirm attacker control, missing sanitization, and reachable runtime context, then fix with the category-appropriate safer API or add a reviewed suppression.

Facts

FactValue
Issue typellm-call-injection
Rule id in SARIF outputsecurity/llm-call-injection
Commandfallow security
Default severityoff
Suppression comment// fallow-ignore-next-line security-sink
Fixable with fallow fixNo
Opt-inYes

Note. Tainted-sink catalogue category; the security-sink suppression token covers every category.