Skill Description Deception Attack against Task Routing in Internet of Agents

A new paradigm, Internet of Agents IoA, is transforming networked systems into LLM-driven service networks, where heterogeneous agents collaborate through task routing based on their self-declared skill descriptions. Although this promising paradigm enables agentic, distributed, and advanced...

Trust Me, Import This: Dependency Steering Attacks Via Malicious Agent Skills

LLM-powered coding agents increasingly make software supply chain decisions. They generate imports, recommend packages, and write installation commands. Prior work showed that these systems can hallucinate non-existent package names, which attackers may register as malicious packages. In this...

PT-2026-39463

A vulnerability was detected in 8421bit MiniClaw 0.8.0/0.9.0. This issue affects the function resolveSkillScriptPath of the file src/kernel.ts of the component System Command Handler. The manipulation results in os command injection. The exploit is now public and may be used. The patch is...

MiniClaw 命令注入漏洞

MiniClaw is an AI memory and evolution tool developed by a personal developer. Versions 0.8.0 and 0.9.0 of MiniClaw contain command injection vulnerabilities. These vulnerabilities stem from the function resolveSkillScriptPath in the System Command Handler component’s src/kernel.ts file, which...

MiniClaw 路径遍历漏洞

MiniClaw is an AI memory and evolution tool developed by a 8421bit individual developer. MiniClaw has a path traversal vulnerability, which stems from the function isPathInside in the executeSkillScript component’s src/kernel.ts file. This vulnerability may lead to path traversal attacks...

@evomap/evolver: Path Traversal in `evolver fetch` default-branch `safeId` allows Hub-controlled overwrite of project files (RCE)

Summary The evolver fetch subcommand in index.js writes Hub-supplied bundledfiles into a directory derived from a Hub-supplied skillid. When --out is not used, the path-sanitizing regex permits . characters, allowing a skillid of .. to escape the skills/ subdirectory and resolve to the user's...

EUVD-2026-27007

Evolver is a GEP-powered self-evolving engine for AI agents. Prior to version 1.69.3, a path traversal vulnerability in the skill download fetch command allows attackers to write files to arbitrary locations on the filesystem. The --out= flag accepts user-provided paths without validation, enabli...

CVE-2026-7596

A vulnerability has been found in nextlevelbuilder ui-ux-pro-max-skill up to 2.5.0. Affected by this issue is the function data.get of the file .claude/skills/design-system/scripts/generate-slide.py of the component Slide Generator. Such manipulation leads to cross site scripting. The attack may ...

coordinated-disclosure

coordinated-disclosure A Claude Code skill + plugin marketpla...

vuln-poc-generate-skill

vuln-poc-generate-skill A Codex skill project for generating...

BadSkill: Backdoor Attacks on Agent Skills Via Model-In-Skill Poisoning

Agent ecosystems increasingly rely on installable skills to extend functionality, and some skills bundle learned model artifacts as part of their execution logic. This creates a supply-chain risk that is not captured by prompt injection or ordinary plugin misuse: a third-party skill may appear...

CVE-2026-40117 PraisonAIAgents Affected by Arbitrary File Read via read_skill_file Missing Workspace Boundary and Approval Gate

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, readskillfile in skilltools.py allows reading arbitrary files from the filesystem by accepting an unrestricted skillpath parameter. Unlike filetools.readfile which enforces workspace boundary confinement, and unlike runskillscript...

CVE-2026-40117 PraisonAIAgents Affected by Arbitrary File Read via read_skill_file Missing Workspace Boundary and Approval Gate

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, readskillfile in skilltools.py allows reading arbitrary files from the filesystem by accepting an unrestricted skillpath parameter. Unlike filetools.readfile which enforces workspace boundary confinement, and unlike runskillscript...

PraisonAI 安全漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 1.5.128 contained security vulnerabilities. These vulnerabilities stemmed from the readskillfile function accepting an unlimited skillpath parameter, which could allow agents to...

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems

Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamined security attack surface. We propose SkillTrojan, a backdoor attack that targets skill implementations rather than model parameters or training...

CVE-2026-22661

prompts.chat prior to commit 0f8d4c3 contains a path traversal vulnerability in skill file handling that allows attackers to write arbitrary files to the client system by crafting malicious ZIP archives with unsanitized filenames containing path traversal sequences. Attackers can exploit missing...

EUVD-2026-18821

prompts.chat prior to commit 0f8d4c3 contains a path traversal vulnerability in skill file handling that allows attackers to write arbitrary files to the client system by crafting malicious ZIP archives with unsanitized filenames containing path traversal sequences. Attackers can exploit missing...

CVE-2026-22661

prompts.chat prior to commit 0f8d4c3 contains a path traversal vulnerability in skill file handling that allows attackers to write arbitrary files to the client system by crafting malicious ZIP archives with unsanitized filenames containing path traversal sequences. Attackers can exploit missing...

CVE-2026-22661 prompts.chat Path Traversal via Skill File Handling

prompts.chat prior to commit 0f8d4c3 contains a path traversal vulnerability in skill file handling that allows attackers to write arbitrary files to the client system by crafting malicious ZIP archives with unsanitized filenames containing path traversal sequences. Attackers can exploit missing...

CVE-2026-22661

prompts.chat prior to commit 0f8d4c3 contains a path traversal vulnerability in skill file handling that allows attackers to write arbitrary files to the client system by crafting malicious ZIP archives with unsanitized filenames containing path traversal sequences. Attackers can exploit missing...