Skip to content
AI News HubLIVE
Original source2 min read

Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems

Summary

arXiv:2609.30383v1 Announce Type: new Abstract: A skill is a modular package of natural-language instructions, executable scripts, and reference resources that an agent can load at runtime to extend its capabilities for a specific task. Skill-based agent systems therefore enable flexible reuse of third-party capabilities, but the openness of this skill ecosystem also opens up a new attack surface. Prior work has focused on vulnerabilities within individual skills, but little attention has been paid to risks that arise from interactions across skills. In this paper, we introduce skill cascading attacks, a threat paradigm in which a malicious objective is distributed across multiple skills so that each modification looks benign in isolation, yet their combined execution is harmful. For inst…

SourcearXiv AIAuthor: Zihao Zhu, Siwei Lyu, Adel Bibi, Baoyuan Wu
Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 24 Sep 2026]

Title:Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems

View a PDF of the paper titled Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems, by Zihao Zhu and 3 other authors

View PDF HTML (experimental)

Abstract:A skill is a modular package of natural-language instructions, executable scripts, and reference resources that an agent can load at runtime to extend its capabilities for a specific task. Skill-based agent systems therefore enable flexible reuse of third-party capabilities, but the openness of this skill ecosystem also opens up a new attack surface. Prior work has focused on vulnerabilities within individual skills, but little attention has been paid to risks that arise from interactions across skills. In this paper, we introduce skill cascading attacks, a threat paradigm in which a malicious objective is distributed across multiple skills so that each modification looks benign in isolation, yet their combined execution is harmful. For instance, in a prescription-review pipeline, the first skill weakens signals of recently discontinued medications in the extracted history, the second downgrades the severity of any drug interaction tied to them, and the third suppresses the resulting low-priority alert in the final summary, so that a severe drug-interaction warning silently disappears before reaching the physician. To systematically study this safety blind spot, we develop SkillCascade, an automated multi-agent red-teaming framework, and release SkillCascade-Bench, a benchmark of 213 validated cascading test cases across multiple agent systems and domains. Across representative agents (e.g., OpenClaw, Claude Code, Codex) and LLM backbones, cascaded interactions reliably induce harmful behaviors while evading existing per-skill scanners and runtime monitors. Our findings highlight a gap between component-level integrity and system-level safety, and call for defenses that reason over cross-skill interactions rather than individual skills in isolation.

Comments: accepted to NeurIPS 2026

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2609.30383 [cs.AI]

(or arXiv:2609.30383v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2609.30383

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Zihao Zhu [view email] [v1] Thu, 24 Sep 2026 18:00:18 UTC (1,373 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems, by Zihao Zhu and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
  • arXiv:2609.30383v1 Announce Type: new Abstract: A skill is a modular package of natural-language instructions, executable scripts, and reference resources that an agent can load a…

Highlights and analysis are generated automatically and may contain errors. Check the original source.