Claude-Skill für systematische MCP-Server-Audits gegen einen kuratierten Best-Practice-Standards-Korpus · 120 Checks · 12 Kategorien · OAuth 2.1, OWASP, Lethal Trifecta, Schweiz-Compliance (DSG/ISDS) · MIT
This grade was produced by analyzer v32 , 1 version behind the one running now. Detectors added since have not been applied here, so it is not directly comparable with a server analyzed at the current version. A re-scan is queued.
- capability exposure inferred + 35
- trust mitigators mixed − 3
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 5m ago · see ecosystem CVEs →
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit ac57e64 · analyzer v32 · 1w ago
skills & prompt files 6
- agent-rules malkreide-mcp-audit-skill-ac57e64/.claude/commands/audit-mcp.md
- skill malkreide-mcp-audit-skill-ac57e64/SKILL.md
- skill malkreide-mcp-audit-skill-ac57e64/mcp-audit.skill!/mcp-audit/SKILL.md
- skill malkreide-mcp-audit-skill-ac57e64/skills/mcp-data-fidelity/SKILL.md
- skill malkreide-mcp-audit-skill-ac57e64/skills/mcp-data-source-probe/SKILL.md
- skill malkreide-mcp-audit-skill-ac57e64/skills/mcp-transport-hardening/SKILL.md
[](https://mcpobservatory.com/servers/github:malkreide/mcp-audit-skill/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of malkreide.