Skip to content
Review

From Instructions to Exploits: Applying Program Analysis to Malicious Agent Skills Across Natural Language and Code

Oct 2026 · 0 citations · 60 references
Computer Science

TL;DR

The Supply-Chain Scanner for Agent Skills (SCS) is presented, a static analysis framework that unifies instructions and code for security analysis that achieves the highest average accuracy, recall, and F1-score among evaluated methods across five LLMs.

Abstract

LLM-powered agents increasingly rely on third-party skills that combine natural-language instructions with executable code, creating supply-chain risks that may span both artifacts. Existing skill scanners often rely on rule matching or direct LLM judgments and provide limited support for tracing such cross-domain behavior. We present the Supply-Chain Scanner for Agent Skills (SCS), a static analysis framework that unifies instructions and code for security analysis. SCS compiles natural-language instructions into a constrained Python-style intermediate representation using a limited set of security-oriented APIs. It then constructs program dependence graphs for instructions and bundled code and connects them into a cross-domain graph (xPDG). A Trust-Sensitivity-Capability (TSC) model propagates security properties over the graph to support structured, largely deterministic risk detection. On a manually verified benchmark of 117 malicious and 117 benign skills, SCS achieves the highest average accuracy (85.6%), recall (95.2%), and F1-score (86.9%) among evaluated methods across five LLMs, with 80.2% precision and average token consumption of 13.7 million. Its NL-to-IR compiler achieves 92.5%-94.5% step-level correctness on 400 human-annotated instruction steps. Finally, analyzing 66,157 real-world ClawHub skills yields 2,473 candidates, of which 627 are confirmed malicious through auxiliary dynamic validation and manual review.

View source

Similar papers

Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents

Skills extend an agent's capabilities by injecting instructions and information into the context, and are widely used by agents such as OpenClaw and Claude Code. Prior work shows third-party marketplaces host malicious skills that give attackers direct influence over the victim's agent. The emerging defense scans skill...

Tobias Kaisar, Aritra Dhar · 0 citations
#artificial intelligence Preprint Nov 2026

RuntimeTickets: Source-Grounded Security Obligations for Agent Skills

Third-party Agent Skills extend what an autonomous agent can do, but a malicious Skill can hide data exposure or output manipulation inside a legitimate workflow. Neither reading a Skill's description nor granting it tool permissions tells whether its execution meets the user's security requirements. We introduce Runti...

Kui-Yi Gao, Xue Liu, Bo-Wei He · 0 citations
#artificial intelligence Preprint Oct 2026

Scan Before You Install: Detecting and Mitigating Local and Composite Vulnerabilities in Skills

A six-module scanner that developed proof-of-concept attacks for each vulnerability, disclosed 10 medium- and high-severity cases to maintainers, and tested mitigations on the remaining cases prevented PoC attacks in all trials while preserving tested legitimate functionality.

P. Gandhi, A. Aviv, Prasanna N. Wudali et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Beyond Maliciousness: Static and Runtime Attack-Surface Profiling of Agent Skills

Agent skills are Markdown documents that a tool-using agent reads as instructions and then acts on with the privileges of the session that loaded them. Installing one grants authority (the standing to direct the agent, not new privilege), and the size of that grant is what we measure. We present a two-phase attack-surf...

Ratnesh Pandey, Japneet Singh, Harsh Akshit et al. · 0 citations
Preprint Oct 2026

Detecting Insecure Compositions of Clean Agent Skills via Capability-Flow Graph Analysis

K KnotScryer is developed to detect insecure skill compositions by treating skills as typed capability flows, and is designed to design a search policy that tracks protected or untrusted data along handoff edges to locate paths reaching insecure operations.

Yi-Hao Li, Chuan-Pu Fu, Yi Zhao et al. · 0 citations
Preprint Oct 2026

PyCache Trap: The Inspection-Execution Gap in Agent Skill Scanners

Agent skills combine instructions with executable resources, giving third-party packages access to an agent's runtime. Existing skill scanners inspect documentation and visible source, but Python may execute a bundled bytecode cache with different behavior. We study this gap between inspection and execution through PyC...

Jie Liao, Si-Meng Qin, Wen-Qi Ren et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.