An AI-skill safety scanner that runs skills with and without decoy resources and compares behavior to detect hidden, conditional malicious actions.
InProceedings of the 5th International Conference onSecurityandPrivacyinCommunicationNetworks,51–70
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SkillSentry: Adaptive Honey Worlds for Dynamic Safety Testing of Agent Skills
An AI-skill safety scanner that runs skills with and without decoy resources and compares behavior to detect hidden, conditional malicious actions.