AI ethics evidence index Search
Source-linked daily record
Evidence record 18775 · automatically gathered

Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents

LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection and instruction bodies for planning. This progressive-disclosure design exposes two sequential control points to untrusted publishers: a static skill may steer an otherwise correct task onto an unnecessarily costly trajectory. Prior work studies selection manipulation, malicious skill instructions, and tool-chain resource amplification largely separately, leaving their end-to-end composition unc

Record details

Published: 12 August 2026
Source: arXiv
Category: Research
Topics: Agents & autonomy · Transparency
Retrieved: 13 August 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Agents & autonomy · Shared topic: Transparency

No One to Blame: A Framework of Constitutive AI Unaccountability

arXiv cs.AI · 12 August 2026

Shared topic: Agents & autonomy · Shared topic: Transparency

Unmasking Toxic Mimicry in Medical Offline Reinforcement Learning for ICU Sepsis Management via Counterfactual Clinical Audits

arXiv cs.CY · 13 August 2026

Shared topic: Agents & autonomy · Shared topic: Transparency

No One to Blame: A Framework of Constitutive AI Unaccountability

arXiv cs.CY · 13 August 2026

Shared topic: Agents & autonomy · Shared topic: Transparency

Governing Agentic AI in FinTech

arXiv cs.CY · 13 August 2026

Shared topic: Agents & autonomy · Shared topic: Transparency

Beyond Memory: A Transactional Continuity Kernel for Long-Lived AI Agents

arXiv · 12 August 2026

Shared topic: Agents & autonomy · Shared topic: Transparency

Reconcile Once, Write Anytime: A Trust-Tiered Librarian and a Multi-Agent Writer for Drift-Free, Point-in-Time Research

arXiv red teaming query · 13 August 2026

How to cite this record

ethics.ai (12 August 2026), “Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents,” evidence record 18775, https://ethics.ai/record/18775 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.