Skills/PyPI/mcp-skillset

mcp-skillset@0.8.6

CAUTION· not started

Publisher claims: "Dynamic RAG-powered skills for code assistants via Model Context Protocol" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher bobmatnyc · publishing for 454 daysInstalls 52Last detonated 5d ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
GITHUB_TOKENOPENROUTER_API_KEYTOKENIZERS_PARALLELISMConfiguration, not credentials: MCP_SKILLSET_DEBUG
Where it talks to
no vendor host named in the codeAlso openrouter.ai, claude.ai, auggie.app, cursor.sh, codeium.com, continue.dev, codex.ai, google.com, owasp.org, simonwillison.net — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names openrouter.ai, claude.ai, auggie.app, cursor.sh, codeium.com, continue.dev, codex.ai, google.com, owasp.org, simonwillison.net as well as its own vendor. The guard injects GITHUB_TOKEN, OPENROUTER_API_KEY, TOKENIZERS_PARALLELISM only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx mcp-skillset

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-09 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Auto-update or dynamic fetch configuration; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
Auto-update or dynamic fetch configurationsrc/mcp_skills/mcp/server.py:89 · Auto-update or dynamic fetch configuration — agent may load new code at runtime# Run auto-update synchronously during startupFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/mcp_skills/mcp/tools/skill_tool.py:429 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/mcp_skills/services/llm_service.py:51 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Check .env files (project root and user home)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/mcp_skills/mcp/tools/skill_tool.py:423 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/mcp_skills/services/llm_service.py:53 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesPath(".env.local"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_skills/services/llm_service.py:37 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files3. .env.local fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_skills/services/auto_updater.py:40 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeconfig: AutoUpdateConfig,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_skills/services/auto_updater.py:47 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeconfig: Auto-update configurationFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcp_skills/services/llm_service.py:38 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files4. .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_skills/models/config.py:305 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file=".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_skills/models/config.py:229 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeauto_update: Automatically update on startupFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcp_skills/cli/commands/ask.py:73 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- .env file: OPENROUTER_API_KEY=sk-or-...Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_skills/mcp/server.py:83 · Auto-update or dynamic fetch configuration — agent may load new code at runtimelogger.info("Auto-update enabled, checking repositories...")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/mcp_skills/cli/config_menu.py:597 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_skills/models/config.py:269 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeenabled: Enable auto-update on MCP server startupFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcp_skills/cli/commands/ask.py:109 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconsole.print(" 3. .env file: OPENROUTER_API_KEY=sk-or-...")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/mcp_skills/models/config.py:383 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file = ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_skills/models/config.py:234 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeauto_update: bool = Field(True, description="Auto-update on startup")Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/mcp_skills/mcp/tools/skill_tool.py:419 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_skills/mcp/server.py:81 · Auto-update or dynamic fetch configuration — agent may load new code at runtime# Auto-update repositories if enabledFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/mcp_skills/mcp/tools/skill_tool.py:38 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_skills/mcp/server.py:82 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeif config.auto_update.enabled:Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/mcp_skills/mcp/tools/skill_tool.py:415 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_skills/services/auto_updater.py:12 · Auto-update or dynamic fetch configuration — agent may load new code at runtimefrom mcp_skills.models.config import AutoUpdateConfigFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/mcp_skills/services/py_mcp_installer/src/py_mcp_installer/utils.py:346 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_skills/models/config.py:264 · Auto-update or dynamic fetch configuration — agent may load new code at runtime"""Auto-update configuration for repository maintenance.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_skills/models/config.py:263 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeclass AutoUpdateConfig(BaseSettings):Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_skills/services/auto_updater.py:33 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeconfig: AutoUpdateConfig with enabled flag and max_age_hoursFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Auto-update or dynamic fetch configurationsrc/mcp_skills/services/auto_updater.py:57 · Auto-update or dynamic fetch configuration — agent may load new code at runtime1. Checks if auto-update is enabledFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcp_skills/services/llm_service.py:32 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Get API key from config, environment, or .env files.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈55 tok
1 file · 80 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for mcp-skillset@0.8.6 as of 5d ago. This is the package itself, not its dependencies.

What would make this Verified

2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim bobmatnyc: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim bobmatnycPropose a patch to the maintainer