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.
Don’t believe everything you read: Understanding and measuring mcp behavior under misleading tool descriptions
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
VIPER-MCP detects and exploits taint-style vulnerabilities in Model Context Protocol servers via anchor-query static analysis and feedback-driven prompt evolution, uncovering 106 zero-day vulnerabilities across 39,884 repositories with 67 CVEs assigned.
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.