Evidence · DiggingBeagle record
OverServe: Resource Amplification Attacks on SaaS Agents
Original paper testing legitimate-task-preserving API call and runtime amplification through tool/prompt pairing.
- Published
- Nov 10, 2026
- Source role
- primary disclosure
Evidence record
Original paper testing legitimate-task-preserving API call and runtime amplification through tool/prompt pairing.
Claim-level citations (2)
- supportsAn attacker made an agent finish its task while multiplying tool calls and elapsed time: OverServe pairs a plausible user task with an MCP tool whose status changes legitimately but slowly. The tool does not need to print a malicious instruction or enter an infinite loop: repeated truthful progress checks induce the agent to poll, retry and accumulate costs. In selected AppWorld tests, median API requests rose from 29 to 2,722.5, a 93.88-fold increase, while the original task completion checks still passed. Other tasks showed smaller amplification; one Enterprise-Worlds configuration hit a fixed 200-call experimental ceiling.
OverServe paper, Table of tool-call amplification and Results, AppWorld Sonnet 29 to 2722.5
- supportsAn attacker made an agent finish its task while multiplying tool calls and elapsed time: The tests are controlled agent benchmarks, not documented unauthorized SaaS invoices. The cost mechanism only occurs when the underlying status evolves slowly enough to keep the agent checking; ordinary successful completion cannot prove that the execution budget was justified. The evidence is bounded by the cited source and test setting. Broader incidence, other environments, and actual production consequences are not established merely by these observations.
Primary disclosure: results, scope and limitations