BIV audits AI agent skills at scale, finding 80% deviate from declared behavior on 49,943 skills and achieving 0.946 F1 for malicious skill detection.
Tensor Trust: Interpretable prompt injection attacks from an online game
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Behavioral Integrity Verification for AI Agent Skills
BIV audits AI agent skills at scale, finding 80% deviate from declared behavior on 49,943 skills and achieving 0.946 F1 for malicious skill detection.