LLM output passed to eval / exec / SQL
Treating LLM output as trusted code or SQL is equivalent to executing user input. A prompt injection attack or a malicious document in the model's context can cause the LLM to output a payload that, when eval'd, executes attacker-controlled commands.
HOW VIBECHECK DETECTS THIS
vibecheck clones your repository and runs Gitleaks, Semgrep, njsscan, and a suite of custom checks targeting patterns common in AI-generated code. This check is part of the AI / LLM Apps category. When a matching pattern is found, Claude triages the finding and produces a plain-English explanation and a concrete fix — no security expertise required.
FREE SCAN
Check your repo for this and 50+ other issues
Connect GitHub → vibecheck scans for secrets, unauthenticated routes, RLS gaps, injection, and more. Claude explains every finding. Free for 2 repos.
scan my repo for free →