The central claim, that legitimate MCP task chains compose into harmful attacks, is supported only by fictional scenarios and isolated benchmark success rates, not by end-to-end demonstrations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H) Agent Unlocks Adversarial Skills
The central claim, that legitimate MCP task chains compose into harmful attacks, is supported only by fictional scenarios and isolated benchmark success rates, not by end-to-end demonstrations.