Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The system replaces unconstrained LLM escalation with a structured, forecast-grounded pipeline and introduces a regulator-aligned evaluation metric for false interventions — two gaps the authors identify as absent from existing DeFi supervision approaches.
The incident demonstrates that `--dangerously-skip-permissions` removes human oversight entirely rather than merely reducing friction, and that `.claude/settings.json` deny rules provide a harder enforcement boundary than confirmation prompts or `CLAUDE.md` instructions alone.
By forcing LLM agents to commit their security assumptions as falsifiable assertions and immediately stress-testing them with a fuzzer, Code-Augur replaces opaque agent reasoning with a verifiable, self-correcting audit loop — directly addressing the missed-vulnerability risk the paper identifies as the central weakness of current agentic security analysis.
The harness directly counters LLM hallucination in compliance contexts by replacing narrative confidence with a mandatory citation-or-silence rule, making every audit finding independently verifiable by opening the cited line.
Vercel Connect removes the need for agents and apps to hold long-lived provider secrets, replacing them with runtime-issued, scoped tokens that can be instantly revoked — directly addressing the credential-leakage and over-permissioning risks common in agentic workflows.
SSG fills the gap between probabilistic prompt instructions and hard enforcement by blocking or redirecting non-compliant agent tool calls before they execute — something prompt files, tool allowlists, and pre-commit hooks each fail to do.
Kintsugi's deterministic rule engine closes a gap left by AI coding agents that execute irreversible shell commands — `rm -rf`, `DROP TABLE`, `dd` — with no native undo, by making destructive actions recoverable via snapshots and ensuring the block decision cannot be subverted by prompt injection.
The `InvokeGuardrailChecks` API removes the requirement to pre-create guardrail resources, giving developers more flexible, granular control over where and when safety checks are applied within multi-turn agentic AI workflows.
The paper demonstrates that source attribution is an independent axis of factuality verification — meaning standard source-blind metrics can pass answers that contain incorrect attributions, a gap ProvenanceGuard is designed to close in MCP-based agents.
The study establishes that explicit delegation contracts improve the reviewability of AI coding agent work — not its correctness — reframing the contract as a mechanism for human oversight rather than a driver of agent task performance.