13 matches found
SkillSpector
SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills used by Claude Code, Codex CLI, Gemini CLI, etc. execute with implicit trust and minimal vetting. In the 31,132-skill analyzed...
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...
SkillSpector v2.11.1
SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills used by Claude Code, Codex CLI, Gemini CLI, etc. execute with implicit trust and minimal vetting. In the 31,132-skill analyzed...
SkillSpector v2.10.0
SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills used by Claude Code, Codex CLI, Gemini CLI, etc. execute with implicit trust and minimal vetting. Research shows that 26.1% of...
SkillSpector v2.8.2
SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills used by Claude Code, Codex CLI, Gemini CLI, etc. execute with implicit trust and minimal vetting. Research shows that 26.1% of...
SkillSpector v2.8.1
SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills used by Claude Code, Codex CLI, Gemini CLI, etc. execute with implicit trust and minimal vetting. Research shows that 26.1% of...
SkillSpector v2.5.3
SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills used by Claude Code, Codex CLI, Gemini CLI, etc. execute with implicit trust and minimal vetting. Research shows that 26.1% of...
SkillSpector v2.5.2
SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills used by Claude Code, Codex CLI, Gemini CLI, etc. execute with implicit trust and minimal vetting. Research shows that 26.1% of...
SkillSpector v2.5.1
SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills used by Claude Code, Codex CLI, Gemini CLI, etc. execute with implicit trust and minimal vetting. Research shows that 26.1% of...
SkillSpector v2.5.0
SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills used by Claude Code, Codex CLI, Gemini CLI, etc. execute with implicit trust and minimal vetting. Research shows that 26.1% of...
Malicious code in skillspector (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 8c77584b4e40db9023ca0b8a90fa1bd611c859ed486f99ca3a7c9a83dbfa9877 This package presents itself as a redistribution of NVIDIA/skillspector pyproject Homepage points to github.com/NVIDIA/skillspector and the source...
MAL-2026-6561 Malicious code in skillspector (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 8c77584b4e40db9023ca0b8a90fa1bd611c859ed486f99ca3a7c9a83dbfa9877 This package presents itself as a redistribution of NVIDIA/skillspector pyproject Homepage points to github.com/NVIDIA/skillspector and the source...
ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree
Agent skills extend AI agents with reusable instructions, tools, scripts, references, and workflows, establishing a security boundary distinct from both model safety and traditional package-malware detection. ClawHub Security Signals is a sanitized dataset of 67,453 latest public OpenClaw skill...