Skill Audit — Security Scanner for MCP Servers & Agent Skills
io.github.eltociear/skill-audit-mcpeltociearstreamable-httpv1.2.1Scanned
MCP server: static security scanner for MCP servers, agent skills & plugins. 17 attack patterns.
11 tools: 6 change things and 5 only read.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 2
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
6 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Skill Audit — Security Scanner for MCP Servers & Agent Skills can do
The Skill Audit — Security Scanner for MCP Servers & Agent Skills is published by the GitHub account eltociear. It has 11 tools. It can create or change data (6 tools: air_quality, earthquakes, public_holidays, country_indicator and 2 more), but cannot delete data. 5 tools only read.
3 tools bring in text other people can write (web_search, read_url and audit_skill_url); 2 tools can send data out of your system (read_url and audit_skill_url).
The fixed checks matched 2 findings (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 19, 2026, version 1.2.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
11 tools
Changes things 6Claude Code: ask
air_qualityCurrent air quality for a place: PM2.5, PM10, ozone, NO2, SO2, CO and dust, plus the US and European AQI and the US AQI band ('Good', 'Unhealthy').No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Current air quality for a place: PM2.5, PM10, ozone, NO2, SO2, CO and dust, plus the US and European AQI and the US AQI band ('Good', 'Unhealthy'). Takes a place name — no coordinates needed. (Free. This server also sells a paid API — call `paid_catalogue` for the routes and prices; x402 over USDC on Base, no signup.)
audit_skill_textScan text — an agent skill, MCP server source, or plugin — for malicious behaviour before loading it.1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...x signatures across 4 severity levels — credential exfiltration, download-and-execute, pro..."
Description, as the server wrote it Scan text — an agent skill, MCP server source, or plugin — for malicious behaviour before loading it. 17 attack patterns / 65 regex signatures across 4 severity levels — credential exfiltration, download-and-execute, prompt injection, command execution, seed-phrase harvesting and more.
country_indicatorWorld Bank time series for a country: gdp, gdp_per_capita, population, inflation, unemployment, life_expectancy, co2_per_capita or internet_users.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it World Bank time series for a country: gdp, gdp_per_capita, population, inflation, unemployment, life_expectancy, co2_per_capita or internet_users. (Free. This server also sells a paid API — call `paid_catalogue` for the routes and prices; x402 over USDC on Base, no signup.)
earthquakesRecent earthquakes from the USGS feed — worldwide, or within a radius of a named place.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Recent earthquakes from the USGS feed — worldwide, or within a radius of a named place. Returns magnitude, depth, tsunami flag and felt reports. (Free. This server also sells a paid API — call `paid_catalogue` for the routes and prices; x402 over USDC on Base, no signup.)
elevationGround elevation in metres for a place name.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Ground elevation in metres for a place name. (Free. This server also sells a paid API — call `paid_catalogue` for the routes and prices; x402 over USDC on Base, no signup.)
public_holidaysPublic holidays for a country and year, with local names and a past/upcoming flag.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Public holidays for a country and year, with local names and a past/upcoming flag. (Free. This server also sells a paid API — call `paid_catalogue` for the routes and prices; x402 over USDC on Base, no signup.)
Only reads 5Show 5 read-only tools
audit_skill_urlFetch a URL and scan what it serves for malicious behaviour.Reads text others writeCan send data out1 finding
Why it is in this group
- The description's first verb is "fetch": a word for reading.
What it can reach
- untrusted-inputThe name "audit_skill_url" says "url": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...x signatures across 4 severity levels — credential exfiltration, download-and-execute, pro..."
Description, as the server wrote it Fetch a URL and scan what it serves for malicious behaviour. 17 attack patterns / 65 regex signatures across 4 severity levels — credential exfiltration, download-and-execute, prompt injection, command execution, seed-phrase harvesting and more.
geocodeResolve a place name to coordinates, country, admin region, timezone, elevation and population.No findings
Why it is in this group
- The description's first verb is "resolve": a word for reading.
Description, as the server wrote it Resolve a place name to coordinates, country, admin region, timezone, elevation and population. (Free. This server also sells a paid API — call `paid_catalogue` for the routes and prices; x402 over USDC on Base, no signup.)
paid_catalogueList the paid API routes this same server offers, with prices and which ones need no input.No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it List the paid API routes this same server offers, with prices and which ones need no input. The MCP tools here are free and general-purpose; the paid routes are specialised (on-chain token safety, live DEX prices, wallet intel, supply-chain scans). Payment is x402 over USDC on Base — no account or API key. Takes no arguments.
read_urlFetch a URL and return its main content as clean Markdown, boilerplate stripped.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "read_url" says "read": a word for reading.
What it can reach
- untrusted-inputThe name "read_url" says "read" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Fetch a URL and return its main content as clean Markdown, boilerplate stripped. (Free. This server also sells a paid API — call `paid_catalogue` for the routes and prices; x402 over USDC on Base, no signup.)
web_searchSearch the live web and return ranked title/url/snippet results, through an automatic multi-engine failover chain.Reads text others writeNo findings
Why it is in this group
- The name "web_search" says "search": a word for reading.
What it can reach
- untrusted-inputThe name "web_search" says "search" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "search" and "web": it reads web pages, which anyone can write.
Description, as the server wrote it Search the live web and return ranked title/url/snippet results, through an automatic multi-engine failover chain. (Free. This server also sells a paid API — call `paid_catalogue` for the routes and prices; x402 over USDC on Base, no signup.)
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:04 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://eltociear-skill-audit.hf.space/mcp: tools/list returned 11 tools to an anonymous client, including air_quality (write), earthquakes (write), public_holidays (write), country_indicator (write), elevation (write) and 1 more
Findings
Matches of fixed checks, with the text they matched.
- Infoaudit_skill_text
The description mentions "credential".
What this check looks forMatched text
description: "...x signatures across 4 severity levels — credential exfiltration, download-and-execute, pro..."
- Infoaudit_skill_url
The description mentions "credential".
What this check looks forMatched text
description: "...x signatures across 4 severity levels — credential exfiltration, download-and-execute, pro..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.2.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http skill-audit https://eltociear-skill-audit.hf.space/mcpclaude mcp add --transport http skill-audit https://eltociear-skill-audit.hf.space/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__skill-audit__paid_catalogue",
"mcp__skill-audit__geocode",
"mcp__skill-audit__web_search"
],
"ask": [
"mcp__skill-audit__air_quality",
"mcp__skill-audit__earthquakes",
"mcp__skill-audit__public_holidays",
"mcp__skill-audit__country_indicator",
"mcp__skill-audit__elevation",
"mcp__skill-audit__read_url",
"mcp__skill-audit__audit_skill_text",
"mcp__skill-audit__audit_skill_url"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as skill-audit. Review it before you use it.
Capability tags behind 3 rules
- mcp__skill-audit__web_search untrusted-input
- mcp__skill-audit__read_url untrusted-input, outbound
- mcp__skill-audit__audit_skill_url untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.eltociear/skill-audit-mcp/verify?hash=fa29a2c75f70e607707330bdf4eaf597e2e08668a14cd7f9c574b92c89aac7ad" | jq -e '.changed == false'Pinned hash fa29a2c75f70, from Nov 19, 2026, 05:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.eltociear/skill-audit-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.eltociear/skill-audit-mcp)Source: MCP Registry · repository. Synced Nov 19, 2026, 05:17 UTC.
Skill Audit — Security Scanner for MCP Servers & Agent Skills: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Skill Audit — Security Scanner for MCP Servers & Agent Skills safe?
- No scan can promise that. What its definitions show: 11 tools, 6 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Skill Audit — Security Scanner for MCP Servers & Agent Skills delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Skill Audit — Security Scanner for MCP Servers & Agent Skills do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Skill Audit — Security Scanner for MCP Servers & Agent Skills have?
- 11 tools: 6 write, 5 read. air_quality, earthquakes, public_holidays, country_indicator, elevation, audit_skill_text, paid_catalogue, geocode and 3 more.
Does the Skill Audit — Security Scanner for MCP Servers & Agent Skills need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Skill Audit — Security Scanner for MCP Servers & Agent Skills send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): read_url and audit_skill_url.
Has the Skill Audit — Security Scanner for MCP Servers & Agent Skills changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 19, 2026.