Type
individual
Skills
2
Claimed
No
Verified
No
Review boundary
Author information helps you judge provenance; different skills from the same author may still have different source states, so review each one before install.
Published skills
Inspect each skill on the cards before install.
Repository: deepsafe-scan
Author: XiaoYiWeio · Source status: Clear source
Universal preflight security scanner for AI coding agents — Detects hooks injection, credential exfiltration & backdoors in .cursorrules, CLAUDE.md, AGENTS.md and more.
Score basis：Clear source · Risk needs review · Universal
Repository: ai-agent-attack-techniques
Author: XiaoYiWeio · Source status: Clear source
A curated list of real-world attacks, vulnerabilities, and techniques targeting AI coding agents (Claude Code, Cursor, OpenClaw, Windsurf, Codex)
Score basis：Clear source · Risk needs review · Universal
