Skills/PyPI/yandex-wiki-search-mcp

yandex-wiki-search-mcp@1.6.0

CAUTION· not started

Publisher claims: "MCP server for Yandex Wiki with full-text search" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher dlbolshov · publishing for 40 daysInstalls 483Last detonated 19 min ago

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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso yandex.ru, yandex.net, yandex.cloud — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx yandex-wiki-search-mcp

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 2026-11-21 and scored it 74/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Collapsed <details> block carrying instructions; 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
Access to sensitive file pathsmcp_wiki/mcp/tools/page_write.py:1034 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# files (.env, secrets) into a wiki, and download would let themFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_main.py:93 · MCP server using network transport (SSE/HTTP) — data sent over network"MCP_SERVER_PUBLIC_URL=https://mcp.test\n",Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
File permission modification commandmcp_wiki/wiki/custom/client.py:371 · File permission modification command — agent changes file ownership/permissions# 3.13, and chmod there toggles nothing but the read-onlyFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_main.py:98 · MCP server using network transport (SSE/HTTP) — data sent over network"MCP_SERVER_PUBLIC_URL=https://mcp.test\nWIKI_TOKEN=abc\n",Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_settings.py:47 · MCP server using network transport (SSE/HTTP) — data sent over networkmcp_server_public_url="https://example.test",Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Collapsed <details> block carrying instructionsREADME.md:79 · Collapsed <details> block carrying instructions<summary><b>Docker (no Python required)</b></summary> ```json { "mcpServers": { "yandex-wiki-search": { "command": "docker", "args": ["run","--rm","-i", "-e","WFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Access to sensitive file pathstests/test_settings.py:143 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(env_dir / ".env").write_text(body, encoding="utf-8")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_settings.py:117 · MCP server using network transport (SSE/HTTP) — data sent over networkmcp_server_public_url=AnyHttpUrl("https://mcp.example.com"),Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Access to sensitive file pathsmcp_wiki/settings.py:24 · 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
MEDIUM
Access to sensitive file pathstests/test_settings.py:200 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesassert not (env_dir / ".env").exists()Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)mcp_wiki/settings.py:110 · MCP server using network transport (SSE/HTTP) — data sent over networkmcp_server_public_url: AnyHttpUrl | None = NoneFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Access to sensitive file pathsmcp_wiki/settings.py:102 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# process environment beats .env whichever name it uses.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_main.py:22 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files(env_dir / ".env").write_text(body, encoding="utf-8")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/test_imports.py:33 · Python subprocess execution detectedresult = subprocess.run( # noqa: S603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_manifest.py:106 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesmonkeypatch.chdir(tmp_path) # no stray .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_settings.py:87 · MCP server using network transport (SSE/HTTP) — data sent over networkmcp_server_public_url=AnyHttpUrl("https://mcp.example.com"),Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Python subprocess execution detectedtests/test_python_range.py:115 · Python subprocess execution detectedtracked = subprocess.run( # noqa: S603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈53 tok
1 file · 56 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

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim dlbolshov: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  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. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. 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 dlbolshovPropose a patch to the maintainer