What Is Skill Poisoning?
6.3BRAINROT SCORESkill Poisoning An attack where malicious instructions are embedded inside an AI agent's installed skill or tool definition itself, causing the agent to behave harmfully when that skill is invoked, without the agent's underlying model being compromised directly.
Origin:Emerged in AI agent and developer security discourse as agent skill ecosystems grew, naming this specific attack vector on the skill layer rather than the model or infrastructure layer.
First Seen:2026-06
Peak Era:2026 (Agent / Developer Security)
Aura Impact:+5 Aura (Catching Skill Poisoning Before Deployment) / -5 Aura (Deploying a Poisoned Skill Into Production)
EXAMPLE USAGE
"Security review caught skill poisoning in a third-party skill, buried instructions that would've exfiltrated data on every call."
Want the full breakdown — categories, trend velocity, platform distribution, and community voting on Skill Poisoning? Visit the full dictionary entry for Skill Poisoning.