@wowok/skills@3.3.1
WoWok AI Skills for Claude Code, Codex, Gemini CLI, Qwen Code, Grok Build, OpenCode, Google Antigravity, Cursor, Devin Desktop (formerly Windsurf), Trae, CodeBuddy, WorkBuddy, Qoder, Cline, Kilo Code and GitHub Copilot - dialogue orchestration layer on to
AI Security Review
scanned 12d ago · by lpm-firewall-aiThe package has an automatic postinstall path that configures its own AI client skills and MCP server, which warrants a warning for agent extension lifecycle risk. Inspected source supports package-aligned setup, not a confirmed malicious attack.
Decision evidence
public snapshot- package.json runs scripts/install.js during postinstall.
- The postinstall resolves client targets and installs skills for them.
- Unless disabled by an environment flag, postinstall ensures and registers an MCP server; it can globally install that server with npm.
- The CLI also exposes explicit init and uninit commands.
- Installer behavior is for this package’s skills and WoWok MCP server; the inspected code does not establish a malicious payload or credential collection.
- The MCP setup can be skipped with WOWOK_SKILLS_NO_MCP.
Source & flagged code
10 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to @wowok/skills@3.3.1.
See all versions of @wowok/skills for other recorded verdicts.
- Review the evidence and your use of @wowok/skills@3.3.1 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.