Analysis of 17k LLM agent skills reveals 520 vulnerable ones with 1,708 leakage issues, primarily from debug output exposure, with a 10-pattern taxonomy and released dataset for future detection.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CR 2years
2026 2roles
background 2polarities
background 2representative citing papers
Conleash uses a risk lattice, policy engine, and refinement loop to deliver scoped, consent-driven authorization for MCP tool calls, reaching 98.2% accuracy and 99.4% escalation catch rate on 984 traces with 8.2 ms overhead and higher user preference in a 16-person study.
citing papers explorer
-
Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study
Analysis of 17k LLM agent skills reveals 520 vulnerable ones with 1,708 leakage issues, primarily from debug output exposure, with a 10-pattern taxonomy and released dataset for future detection.
-
Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization
Conleash uses a risk lattice, policy engine, and refinement loop to deliver scoped, consent-driven authorization for MCP tool calls, reaching 98.2% accuracy and 99.4% escalation catch rate on 984 traces with 8.2 ms overhead and higher user preference in a 16-person study.