Proprietary LLM agent skills can be extracted via black-box prompt attacks using an automated generation pipeline, creating serious copyright risks that partial defenses do not fully eliminate.
Specification - model context protocol,
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
-
Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study
Proprietary LLM agent skills can be extracted via black-box prompt attacks using an automated generation pipeline, creating serious copyright risks that partial defenses do not fully eliminate.