SkillSpector
Named by 4 kept items in this workspace.
Search every workspace for SkillSpector. It matches the name as written, so it can find other things that share it.
The items that name it 4
Open source scanner purpose-built for the skill layer; found vulnerabilities in 26.1% of scanned skills and likely malicious intent in 5.2%
Security scanner for AI-agent skills (Claude Code, Codex CLI, Gemini CLI): static analysis, AST/YARA/taint checks, LLM semantic review, MCP least-privilege/tool-poisoning checks, SARIF/JSON/Markdown output
Architecturally similar scan-before-install tool with SARIF/JSON output and an LLM semantic stage for intent-level detection (e.g., a skill claiming to format code while reading ~/.ssh); backed by an empirical study scanning 42,447 skills, finding 26.1% vulnerable.
Security scanner for AI agent skills; detects vulnerabilities, malicious patterns, and security risks before installing agent skills. Part of the NVIDIA Verified Skills pipeline (scans, evaluates, and signs agent skills before publication).
All technologies in this workspace.