← 研踪 PaperTrailarXiv:2611.12155 · v1
StealthyPoison: Manipulating LLM Agent Behavior through Procedural Poisoning of Third-Party Skills
首次提交 2026-11-09 18:05
版本更新 2026-11-09 18:05
雷达观测 2026-11-10 15:22
摘要
LLM agents increasingly retrieve third-party skills from public registries and follow their procedures to complete user tasks. This reliance allows attackers to manipulate agent behavior by poisoning the skills. However, overtly malicious instructions can provide explicit signals for detection. We present StealthyPoison, a stealthy procedural poisoning attack that corrupts a skill's decision-critical rules to induce incorrect task outcomes while preserving its advertised functionality and normal execution. Unlike prior knowledge corruption attacks that craft poisoned content for known target question-answer pairs, StealthyPoison constructs reusable poisoned procedures from a publicly available third-party skill, without access to actual user requests or their ground-truth answers. To make the poisoned procedure generalize to unseen requests, it first synthesizes requests from the target skill and executes its clean version using a surrogate agent to obtain pseudo-references. These references and surrogate execution feedback guide the iterative refinement of payloads that alter decision-critical rules. To increase the likelihood that the poisoned skill is retrieved and selected over benign alternatives, the attack augments the poisoned skill's retrieval metadata with independently generated request descriptions. We evaluate StealthyPoison on 566 eligible target skills and 5,244 requests against more than 26,000 registry entries. It improves top-1 poisoned-skill placement by 13.6% relative to both HotFlip and GCG. Constructed using feedback from a single surrogate model, the procedural poisoning payloads transfer effectively and without modification to three held-out victim models and achieve end-to-end attack success in a Claude Code workflow powered by Opus 4.8. The defense evaluation further shows that most of these payloads evade detection by both SkillSpector and GPT-5.4-mini.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-09 18:05 · 最新观测版本
StealthyPoison: Manipulating LLM Agent Behavior through Procedural Poisoning of Third-Party Skills
LLM agents increasingly retrieve third-party skills from public registries and follow their procedures to complete user tasks. This reliance allows attackers to manipulate agent behavior by poisoning the skills. However, overtly malicious instructions can provide explicit signals for detection. We present StealthyPoison, a stealthy procedural poisoning attack that corrupts a skill's decision-critical rules to induce incorrect task outcomes while preserving its advertised functionality and normal execution. Unlike prior knowledge corruption attacks that craft poisoned content for known target question-answer pairs, StealthyPoison constructs reusable poisoned procedures from a publicly available third-party skill, without access to actual user requests or their ground-truth answers. To make the poisoned procedure generalize to unseen requests, it first synthesizes requests from the target skill and executes its clean version using a surrogate agent to obtain pseudo-references. These references and surrogate execution feedback guide the iterative refinement of payloads that alter decision-critical rules. To increase the likelihood that the poisoned skill is retrieved and selected over benign alternatives, the attack augments the poisoned skill's retrieval metadata with independently generated request descriptions. We evaluate StealthyPoison on 566 eligible target skills and 5,244 requests against more than 26,000 registry entries. It improves top-1 poisoned-skill placement by 13.6% relative to both HotFlip and GCG. Constructed using feedback from a single surrogate model, the procedural poisoning payloads transfer effectively and without modification to three held-out victim models and achieve end-to-end attack success in a Claude Code workflow powered by Opus 4.8. The defense evaluation further shows that most of these payloads evade detection by both SkillSpector and GPT-5.4-mini.
查看此版本解读 →查看此版本原文 ↗