models — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited models (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
{% set server = colin.mcp.source.server_info() %} {% set server_name = vars.mcp_provider_name | default(server.name) %} {% set skill_name = server_name | lower | replace(" ", "-") %} {% file skill_name ~ "/SKILL.md" publish=true %}
name: {{ skill_name }} description: {% llm model="anthropic:claude-haiku-4-5" id="skill-description" %}Write a 1-sentence description of this MCP server's capabilities for use as a skill description. Be concise.
Server name: {{ server.name }} Server description: {{ server.instructions or "No description provided" }} {%- endllm %} {% if vars.generate_scripts | default(true) %} allowed-tools: Read, Bash(python:*) {%- endif %}
{{ server.instructions }}
{% if vars.generate_scripts | default(true) %}
This skill includes Python scripts in scripts/ that call MCP tools directly.
To use these scripts, install: pip install fastmcp
{% endif %} {% set tools = colin.mcp.source.list_tools() %}
This server provides {{ tools | length }} tool(s):
{% for tool in tools %} {% set tool_doc = ref(skill_name ~ "/" ~ tool.name ~ ".md") %}
{% endfor %} {% endfile %}
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.