These findings establish that static analysis alone is insufficient for skill security, motivating defense-in-depth architectures that combine fast static pre-screening with semantic review.
Abstract
Agent Skills---structured packages of instructions and scripts that augment LLM-based agents---are rapidly proliferating, yet their security properties remain under-explored. We present \textsc{SkillsMetric}, a five-stage static analysis framework that scores skill packages along pattern density, statistical anomaly, dataflow taint, import anomaly, and capability mismatch dimensions. We construct an adversarial evaluation dataset of 2{,}266 skills spanning 16~attack types across code-level, system-level, and semantic-level threats, and evaluate on the full SkillMD-138K corpus. Our framework achieves an AUC of 0.93 and 5-fold cross-validated F1 of 73.4\%$\pm$0.5\%, with strong detection of data exfiltration (93\%) and steganographic payloads (93\%). Crucially, we identify fundamental blind spots: \emph{host destruction} attacks using common shell commands evade all five stages (0\% detection), and \emph{prompt injection} via natural-language manipulation achieves only 42\% detection. These findings establish that static analysis alone is insufficient for skill security, motivating defense-in-depth architectures that combine fast static pre-screening with semantic review.
An adversarial skill-synthesis method using six LLMs across four families to transform 471 real-world shell commands into benign-appearing skills, released as a benchmark of 2,826 skills mapped to 11 MITRE ATT&CK tactics.
Rui Yang, Michael Fu, Kla Tantithamthavorn et al.· 0 citations
The results show that reliable malicious-Skill detection requires both broader cross-source benchmark coverage and evaluation that jointly measures attack detection and benign over-flagging.
Agent skills are emerging as an important attack surface in LLM-based agent systems. Through an empirical study of existing skill scanners, we find that current defenses mainly inspect individual skills, leaving risks from cross-skill composition insufficiently examined. This creates a practical blind spot: multiple locally plausible skills may pass security checks while collectively forming a harmful workflow during agent execution. To investigate this threat, we propose ColluSkill, a collusive multi-skill-chain attack framework that decomposes a complete malicious intent into interdependent sub-payloads embedded in independently packaged skills. The attack does not rely on any single malicious skill, but emerges from the ordered composition of locally plausible behaviors through contextual dependencies, artifact passing, and execution handoffs. ColluSkill further employs LLM-based chain planning and scanner-feedback refinement to preserve chain-level attack semantics while reducing suspicious signals in individual sub-skills. To defend against such attacks, we propose ChainGuard, a context-aware skill-chain scanner that jointly analyzes a candidate skill and the skills already installed in the agent environment. ChainGuard reconstructs cross-skill dependencies, artifact flows, capability compositions, and downstream behaviors to identify risks that emerge only at the workflow level. Experiments on six representative skill scanners show that ColluSkill achieves an average attack success rate of 96.0% and consistently outperforms the evaluated single-skill and multi-skill attack baselines. Meanwhile, ChainGuard reduces the attack success rate to 22.5% while allowing 99.5% of benign workflows to pass, highlighting the importance of chain-level security analysis for agent skill ecosystems.
Puyu Zeng, Simeng Qin, Jingzhi Li et al.· 1 citation
SkillShield is introduced, a system-prompt defense that synthesizes security skills offline from known attacks or recorded agent failures to prevent harmful actions and malware generation for LLM coding agents.
Xiaodong Wu, Zhimin Zhao, Qi Li et al.· 0 citations
Experimental results show that LLMs, when guided by rubric-based prompts and supplemented with ATT&CK domain knowledge, achieve robust performance across detection, localization, and TTP mapping tasks.
Joon-Young Gwak, Aubrey Strier, Zhaohan Xi et al.· 0 citations
Script-based malware remains a prevalent attack technique. These scripts often contain indicators of compromise (IOCs) that provide actionable threat intelligence. However, statically recovering such indicators is challenging, as relevant values may be dispersed or transformed within code. Although large language models (LLMs) have shown promise in security analysis, their ability to recover IOCs from malicious scripts remains underexplored. We present SCRIPTIOC-BENCH, a benchmark for measuring static IOC extraction capability on real-world malicious scripts. The benchmark comprises 634 manually verified JavaScript, PowerShell, and VBScript malware samples covering four IOC types (URLs, domains, IP addresses, and filesystem artifacts). We further stratify ground-truth IOCs by recovery level, distinguishing directly exposed indicators from those requiring decoding or reconstruction. Using this benchmark, we evaluate a broad range of proprietary and open-weight LLMs and show that IOC recovery without execution remains challenging across model scales: the strongest model reaches only 65.4 F1. To characterize how recovery fails, we introduce a false-positive taxonomy and use it to compare the error profiles of the evaluated models. We further study two mitigations on a small open-weight model, deterministic string utilities and task-specific adaptation, finding that they provide complementary recovery gains, raise precision, and shift errors toward sample-grounded mismatches.
Hanna Kim, Jian Cui, Minkyoo Song 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.
