Refuses a shell, file, web fetch or MCP call that holds the signed-in account's email address beside a word that declares who is calling, so the address does not go out as a client's identity, and refuses a user-tier plugin's own read of the session's identity.
- Stars
- 156,493
- Version
- v5
- Copies
- 0
Overview
Waxell's checks found 1 finding to review, highest severity medium.
- Highest severity
- medium
- Findings
- 1
- What ran
- Static analysis + deep scan
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
We don't republish the plugin's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked today
Result
Review findings Waxell's checks found 1 finding to review, highest severity medium.
Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work
Findings (1)
medium · 1
- medium
Privilege Escalation: Sudo/Root Execution
README.md:81 · skillspector:PE2
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v5 (0.1.0)2026-11-211 changed Review findings
- v4 (0.1.0)2026-11-191 changed Review findings
- v3 (0.1.0)2026-11-182 changednot checked
- v2 (0.1.0)2026-11-172 changednot checked
- v1 (0.1.0)2026-11-16 Review findings
Files
Files
12 files, 29 KB in total. Names only; open them on GitHub.
- .claude-plugin/plugin.json
- README.md
- hooks/hooks.json
- hooks/index.ts
- hooks/outbound/index.ts
- hooks/outbound/names-user-agent.ts
- hooks/outbound/outgoing-text.ts
- hooks/outbound/refusal.ts
- hooks/outbound/script-names.ts
- hooks/outbound/shell-tools.ts
- hooks/outbound/text-of.ts
- hooks/register.ts
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More engineering skills and plugins
sec-defaultAnthropicSecurity default for organizations: seated outermost, it keeps the organization's classic hooks, prompt content, settings, tool policy and… Review findingsEngineeringFinance156k
security-auditCloudflareSecurity guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions,… No issuesEngineeringSecurity76k
technical-writerVercelWrite, review, and edit developer documentation for SDKs, libraries, and frameworks, including sites such as agent-browser.dev and… No issuesEngineeringResearch53k
fakechatAnthropicLocalhost iMessage-style web chat for Claude Code, test surface with file upload and edits. No tokens, no access control. No issuesEngineeringAI & agents48k