BadSkill poisons embedded models in agent skills to achieve up to 99.5% attack success rate on triggered tasks with only 3% poison rate while preserving normal behavior on non-trigger inputs.
Mitigating poison- ing attacks on machine learning models: A data provenance based approach
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning
BadSkill poisons embedded models in agent skills to achieve up to 99.5% attack success rate on triggered tasks with only 3% poison rate while preserving normal behavior on non-trigger inputs.