Answers are grounded in this paper and cite their sources.
AI coding harnesses couple language models to shells, filesystems, and network sockets, turning the harness into an automated Living-off-the-Land (LotL) platform: once an adversary injects instructions into retrieved content, dual-use binaries such as bash, curl, and find become the payload. We argue that security in agentic systems is a structural property of the cognitive architecture and permission composition rather than an emergent property of individual models. Static regex blacklists miss structural evasions, whereas LLM-as-a-Judge guardrails incur high latency while over-blocking benign work. We present ActiveSecHarness, a neurosymbolic reference-monitor architecture built around Separation of Intelligence and Authority. It combines (1) Macaroon-inspired HMAC capability tokens across four Trust and Authority Rings, (2) a 2D product taint lattice L = Lₜᵣᵤₛₜ × Lₛₑₙₛ and a workspace provenance ledger that prevents secret laundering across disk, (3) deterministic Ring-0 OS/tool guards, and (4) bytecode certificates, split-horizon audit logs, self-healing security test synthesis, and an adaptive UserWikiManager. Across $N=252$ fixtures ($120$ attack, $120$ benign, $12$ kill chains), a live local LLM judge (qwen3:4b) refuses $98.3%$ of benign work at 142.3\,ms latency, whereas Ring 0 achieves ABR=1.000 and FPR=0.000 in 12.7\,μs (11,200× faster). In a multi-step trajectory ablation, an oracle Conseca-style stateless policy misses $4/12$ kill chains (ABR=0.667) and coarse Boolean taint blocks $83.3%$ of benign workflows, while our 2D product lattice achieves ABR=1.000 and FPR=0.000 at ≈ 20\,μs per step.
No takes yet. Share an insight, caveat, or question.
Hegelich et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: