Improper Output Handling

Hunt improper LLM output handling (OWASP LLM05:2025) — downstream code that trusts unstructured model output and renders / executes / shells it without sanitisation, producing XSS, SSRF, SQL injection, RCE, and SSTI via the model channel.

purpleailab Updated 6.6k repo stars
Decepticon — XBOW pass rate 102/104 (98.08%)

File contents

purpleailab/decepticon commit 381ef28abc

Frequently asked questions

npx get-skill add purpleailab/improper-output-handling