[2607.12340] Skills That Don't Exist: A Large-Scale Study of Hallucinated Skill Recommendation in LLM Agents

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Software Engineering

arXiv:2607.12340 (cs)

[Submitted on 14 Jul 2026]

Title:Skills That Don't Exist: A Large-Scale Study of Hallucinated Skill Recommendation in LLM Agents

Authors:Weifeng Yuan, Wenbo Guo, Feng Dong, Haoyu Wang, Yang Liu<br>View a PDF of the paper titled Skills That Don't Exist: A Large-Scale Study of Hallucinated Skill Recommendation in LLM Agents, by Weifeng Yuan and 4 other authors

View PDF<br>HTML (experimental)

Abstract:LLM agents acquire new capabilities by downloading skills from open registries. Instead of browsing these catalogs manually, developers typically ask the agent to recommend and install a skill. This convenience hides a risk: agents frequently invent names for skills that exist in no registry. We term this flaw skill name hallucination. A fake name may seem harmless, but it opens the door to supply-chain attacks. Because registries rarely verify publishers, an adversary can prompt the agent, collect the fake names it returns, pre-register malicious skills under them, and wait for a victim to install the payload. We conducted the first large-scale measurement of skill name hallucination, evaluating 15,000 prompts across 12 configurations (4 standalone LLMs and 8 agents). We conservatively counted a name as hallucinated only if it was missing from all live registries and GitHub. The results reveal a systemic vulnerability: every configuration hallucinates. Rates average 36.0% for standalone LLMs and 36.9% for agents, rising to 43.1% on real-world developer questions. In total, the systems generated 5,669 distinct hallucinated names. Crucially, these names are not random noise. Agents repeat the same fake names across prompts and models, giving attackers highly reliable targets to hijack. Finally, we tested four model-level defenses and found a severe conflict between security and usability. The strongest, retrieval grounding, cut the hallucination rate from 40.8% to 3.2% but crippled usefulness: even the best-defended system recommended the correct skill only about one in six times. Skill name hallucination is thus a highly exploitable vulnerability requiring minimal attacker effort. Fixing it cannot rely on prompt engineering or model tuning alone. It demands ecosystem-wide structural changes: registry-level name reservations and verified recommendation pipelines.

Subjects:

Software Engineering (cs.SE); Cryptography and Security (cs.CR)

Cite as:<br>arXiv:2607.12340 [cs.SE]

(or<br>arXiv:2607.12340v1 [cs.SE] for this version)

https://doi.org/10.48550/arXiv.2607.12340

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Wenbo Guo [view email]<br>[v1]<br>Tue, 14 Jul 2026 04:40:45 UTC (661 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Skills That Don't Exist: A Large-Scale Study of Hallucinated Skill Recommendation in LLM Agents, by Weifeng Yuan and 4 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.SE

next >

new<br>recent<br>| 2026-07

Change to browse by:

cs<br>cs.CR

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

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...