AI security research / articles
Analysis across cases.
43 Articles · Page 6 of 9
5 matching records on this page
From the archive
Prompt filters can miss hostile instructions, agents can misuse legitimate authority, and synthetic media can make identity checks less reliable. Three Habr pieces converge on a stronger defensive pattern: place deterministic policy, least privilege or independent verification between recognition and the next consequential action.
Recent agent incidents make the near-term control problem concrete: permissions, egress, supervision, dependency and incident accountability are already under strain, even though the strongest futurist loss-of-control scenario remains unobserved.
DG-VDT reports strong zero-shot results for classifying three Ethereum vulnerability types from EVM execution traces, but the headline latency measures model inference after trace generation, not end-to-end auditing. The strongest result is promising benchmark evidence rather than an independently reproduced production capability.
Five 2026 records show how workflow nodes, agent skills, MCP servers and memory plugins can become private-data attack paths once they inherit legitimate authority. The evidence does not support blaming free or open-source software as a class: the documented failures include malicious third-party packages, compromised legitimate releases, mutable remote semantics and a separate product authorization bug.
Smart-contract audit skills can materially improve a strong agent, but the September 2026 evidence makes activation and verification part of the real audit stack. That puts the new result beside EchoFuzz, KASS and EVAge without confusing defensive auditing with exploit automation.
No matches on this page.