data-and-model-poisoning

star 4.4k

Hunt LLM training-data and model poisoning (OWASP LLM04:2025) — adversarial inputs that bias future model behaviour through fine-tuning, RLHF, or continuous-learning loops.

By PurpleAILAB schedule Updated 6/2/2026

play_arrow Run Skill in Manus View GitHub

Skill instructions (SKILL.md) could not be loaded from local cache or raw GitHub repository.

Install via CLI

npx skills add https://github.com/PurpleAILAB/Decepticon --skill data-and-model-poisoning

Repository Details

star Stars 4,393

call_split Forks 875

navigation Branch main

article Path SKILL.md

Occupations

Information Security Analysts