Grade B
Skill Audit — Security Scanner for MCP Servers & Agent Skills
io.github.eltociear/skill-audit-mcp · v1.2.1 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
MCP server: static security scanner for MCP servers, agent skills & plugins. 17 attack patterns.
Source: https://github.com/eltociear/skill-audit-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 11 tool(s) to anyone, no credentials needed. |
| Medium | MW002 | Package ghcr.io/eltociear/skill-audit-mcp:mcp-1.2.0 is published without a fixed version. |
What was checked
- https://eltociear-skill-audit.hf.space/mcp: answers without auth
- oci: ghcr.io/eltociear/skill-audit-mcp:mcp-1.2.0@? (static checks only; code not executed)
Public tools: paid_catalogue, air_quality, geocode, earthquakes, public_holidays, country_indicator, elevation, web_search, read_url, audit_skill_text, audit_skill_url
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-eltociear-skill-audit-mcp-0113bdbc)