SkillShield: Prompt-Space Security Skills for LLM Coding Agents

• URL: http://arxiv.org/abs/2608.25817v1
• Date: Wed, 26 Aug 2026 14:00:11 GMT
• Title: SkillShield: Prompt-Space Security Skills for LLM Coding Agents
• Abstract summary: SkillShield is a system-prompt defense that synthesizes security skills offline from known attacks or recorded agent failures.<n>It protects the system by defining the security policies the model should follow during execution.<n>Across six large language models on RedCode, the default all-classes skill reduces malware-generation severity from 3.37 to 0.58 and achieves a 43.6% execution attack success rate.
• Score: 20.042094810707166
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A coding agent edits files and executes shell commands with its developer's privileges, allowing malicious requests to translate directly into harmful actions or functional malware. Existing defenses have complementary limitations: weight-level alignment is unavailable to API-only deployers, whereas input filters and execution-boundary monitors require auxiliary classification or checking components along the agent's trajectory. We therefore introduce SkillShield, a system-prompt defense that synthesizes security skills offline from known attacks or recorded agent failures. These skills are injected into the system prompt at session start and remain active throughout the tool-use loop. Unlike a reference monitor, they protect the system by defining the security policies the model should follow during execution. Due to the limited system-prompt space, we examine three fixed-budget provisioning scopes: all-classes, with one skill covering all threat classes, per-bundle, with one skill targeting a related subset, and per-class, with one skill dedicated to a single known class and used as the upper-bound reference. None requires runtime request classification or routing. Across six large language models on RedCode, the default all-classes skill reduces malware-generation severity from 3.37 to 0.58 and achieves a 43.6% execution attack success rate, comparable to Llama Guard 3's 42.7% without its separate 8B classifier. The per-bundle and class-fixed per-class settings further reduce this rate to 36.2% and 14.5%, respectively. Under two non-adaptive jailbreak families, SkillShield continues to outperform all baselines on malware generation. Across 731 benign task descriptions, SkillShield yields a mean safety-refusal rate of 0.14%. These results demonstrate the potential of prompt-space security skills to prevent harmful actions and malware generation for LLM coding agents.

Related papers

• Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection [8.339789704552706]
  We present SkillGuard, a harness-level enforcement layer that treats contamination as contamination and restricts future capabilities to disconnect the resulting state from deployer-defined forbidden states.<n>We evaluate SkillGuard on four AgentDojo suites with two backend LLMs, Gemini 2.5 Flash and Llama3.3-70B, against an LLM-only No Defense baseline and three defenses at different system layers.
  arXiv  Detail & Related papers  (2026-08-30T20:57:47Z)
• StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing [80.39644823192113]
  We propose StepGuard, a step-level guard model that can audit completed agent trajectories and check tool actions before they are executed.<n>StepGuard achieves the highest average accuracy among open-weight guard models, with performance comparable to GPT-5.4.<n>When used to guard agents on AgentDojo and AgentDyn, StepGuard reduces mean attack success rate by 77.3%.
  arXiv  Detail & Related papers  (2026-08-25T16:17:27Z)
• Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens [65.53494487819053]
  Claw-like AI agents (e.g., OpenClaw) are always-on processes with persistent access to credentials, files, tools, and external services.<n>We adopt a computer-system analogy: treating a Claw-like agent as an agentic computer system whose gateway runtime plays an OS-like mediation role.<n>We develop SafeClawArena, a benchmark of 406 adversarial tasks across four attack surfaces.
  arXiv  Detail & Related papers  (2026-06-29T18:00:45Z)
• SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills [0.0]
  We present SKILLVETBENCH, a live public leaderboard on Hugging Face that uses an LLM-as-Judge to vet agent skills.<n>S SARS (Skill Agentic Risk Score) is a five-dimensional agentic-risk metric with a principled weighted formula for instruction-following systems.
  arXiv  Detail & Related papers  (2026-06-14T16:30:33Z)
• SkillMutator: Benchmarking and Defending Language-and-Code Cross-modal Attacks on LLM Agent Skills [7.465256215885481]
  Large language model (LLM) agents increasingly extend their capabilities at runtime by loading Agent Skills.<n>Because a skill's behavior relies on both natural-language instructions and executable code, assessing its safety requires cross-modal reasoning.<n>We introduce SkillMutator, the first benchmark for install-time detection of language-and-code cross-modal attacks on Agent Skills.
  arXiv  Detail & Related papers  (2026-06-12T06:27:12Z)
• SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction [89.03272793385054]
  Agent skills occupy a privileged position in the agent workflow, rendering third-party skills a vulnerable attack surface.<n>We introduce SkillHarm, a benchmark of skill-based attacks across the skill-use lifecycle.<n>We show that current agents remain vulnerable with attack success rates up to 86.3% in FPP and 69.3% in SMP.
  arXiv  Detail & Related papers  (2026-06-01T17:45:39Z)
• Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems [35.65937852381774]
  Document-Driven Implicit Payload Execution (DDIPE) embeds malicious logic in code examples and configuration templates within skill documentation.<n>We generate 1,070 adversarial skills from 81 seeds across 15 MITRE ATTACK categories.<n>DDIPE achieves 11.6% to 33.5% bypass rates, while explicit instruction attacks achieve 0% under strong defenses.
  arXiv  Detail & Related papers  (2026-04-03T14:58:58Z)
• Internal Safety Collapse in Frontier Large Language Models [65.00730294617382]
  This work identifies a critical failure mode in frontier large language models (LLMs)<n>Under certain task conditions, models enter a state in which they continuously generate harmful content while executing otherwise benign tasks.<n>We introduce TVD, a framework that triggers ISC through domain tasks where generating harmful content is the only valid completion.
  arXiv  Detail & Related papers  (2026-03-04T12:55:34Z)
• Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks [27.120130204872325]
  We introduce SkillInject, a benchmark evaluating the susceptibility of widely-used LLM agents to injections through skill files.<n>SkillInject contains 202 injection-task pairs with attacks ranging from obviously malicious injections to subtle, context-dependent attacks hidden in otherwise legitimate instructions.<n>Our results show that today's agents are highly vulnerable with up to 80% attack success rate with frontier models.
  arXiv  Detail & Related papers  (2026-02-23T18:59:27Z)
• AI Security Beyond Core Domains: Resume Screening as a Case Study of Adversarial Vulnerabilities in Specialized LLM Applications [71.27518152526686]
  Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content moderation.<n>LLMs can be manipulated by "adversarial instructions" hidden in input data, such as resumes or code, causing them to deviate from their intended task.<n>This paper introduces a benchmark to assess this vulnerability in resume screening, revealing attack success rates exceeding 80% for certain attack types.
  arXiv  Detail & Related papers  (2025-12-23T08:42:09Z)
• AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents [84.96249955105777]
  LLM agents may pose a greater risk if misused, but their robustness remains underexplored.<n>We propose a new benchmark called AgentHarm to facilitate research on LLM agent misuse.<n>We find leading LLMs are surprisingly compliant with malicious agent requests without jailbreaking.
  arXiv  Detail & Related papers  (2024-10-11T17:39:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.