Skills/PyPI/redshift-comment-mcp

redshift-comment-mcp@0.12.0

CAUTION· not started

Publisher claims: "A Model-Context Protocol server for Amazon Redshift." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher kouko · publishing for 55 daysInstalls 112Last detonated 1 h 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
REDSHIFT_PASSWORDConfiguration, not credentials: REDSHIFT_COMMENT_PROFILE
Where it talks to
no vendor host named in the code
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. It asks for REDSHIFT_PASSWORD and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --net declared -- uvx redshift-comment-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 2026-11-15 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hidden zero-width characters detected; Hidden zero-width characters detected; Privileged sudo command. 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
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

HIGH
Hidden zero-width characters detectedsrc/redshift_comment_mcp/redshift_tools.py:426 · Hidden zero-width characters detected — may conceal content"​" # ZERO WIDTH SPACEFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
File permission modification commandsrc/redshift_comment_mcp/config.py:396 · File permission modification command — agent changes file ownership/permissionsthan 0600 at any instant; the explicit chmod puts the mode back where aFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Hidden zero-width characters detectedsrc/redshift_comment_mcp/redshift_tools.py:425 · Hidden zero-width characters detected — may conceal content"" # BOMFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
HIGH
Privileged sudo commandsrc/redshift_comment_mcp/redshift_tools.py:1648 · Privileged sudo command — agent may execute with elevated privileges# (mode 000, a root-owned file from a sudo install, a directoryFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known package.github/workflows/publish.yml:198 · npx invocation of non-well-known package — may execute untrusted coderun: npx -y @anthropic-ai/mcpb pack mcpb dist/redshift-comment-mcp.mcpbFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Hidden zero-width characters detectedsrc/redshift_comment_mcp/redshift_tools.py:428 · Hidden zero-width characters detected — may conceal content"‍" # ZERO WIDTH JOINERFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
CRITICAL
Pipe-to-shell patternsrc/redshift_comment_mcp/redshift_tools.py:217 · Pipe-to-shell pattern — downloads and immediately executes remote code# here. Raw, a host of ``h.example.com; curl … | sh #`` turns one printedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
File permission modification commandsrc/redshift_comment_mcp/config.py:399 · File permission modification command — agent changes file ownership/permissionsThat chmod runs after ``os.replace`` — the point of no return — so aFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Hidden zero-width characters detectedsrc/redshift_comment_mcp/redshift_tools.py:427 · Hidden zero-width characters detected — may conceal content"‌" # ZERO WIDTH NON-JOINERFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
File permission modification commandtests/test_config.py:203 · File permission modification command — agent changes file ownership/permissions}, "the content did not actually land despite the chmod failure being tolerated"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Hidden zero-width characters detectedtests/test_tools.py:959 · Hidden zero-width characters detected — may conceal content"SELECT 1",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Pipe-to-shell patterntests/test_tools.py:1706 · Pipe-to-shell pattern — downloads and immediately executes remote code``h.example.com; curl … | sh #`` turns the printed line into twoFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Process kill commandsrc/redshift_comment_mcp/config.py:331 · Process kill command — agent can terminate processesA SIGKILL, an OOM kill or a power loss between ``mkstemp`` andFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shellsrc/redshift_comment_mcp/redshift_tools.py:217 · Remote installer piped to shell# here. Raw, a host of ``h.example.com; curl … | sh #`` turns one printedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
File permission modification commandtests/test_config.py:1268 · File permission modification command — agent changes file ownership/permissions"""``write_text`` creates at 0644 under the default umask, chmod second."""Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Hidden zero-width characters detectedtests/test_tools.py:946 · Hidden zero-width characters detected — may conceal contentfor prefix in ('', '​', ' ', '⁠'):Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Python subprocess execution detectedsrc/redshift_comment_mcp/setup_cli.py:115 · Python subprocess execution detectedcaptured into a local Python string via ``subprocess.run(capture_output=Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Hidden zero-width characters detectedtests/test_tools.py:960 · Hidden zero-width characters detected — may conceal content"​ WITH cte AS (SELECT 1 x) SELECT * FROM cte",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
Remote installer piped to shelltests/test_tools.py:1706 · Remote installer piped to shell``h.example.com; curl … | sh #`` turns the printed line into twoFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedsrc/redshift_comment_mcp/setup_cli.py:172 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/redshift_comment_mcp/setup_cli.py:134 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Hidden zero-width characters detectedtests/test_tools.py:979 · Hidden zero-width characters detected — may conceal content("​ ", "Empty"),Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
MEDIUM
File permission modification commandtests/test_config.py:1272 · File permission modification command — agent changes file ownership/permissionsreal_chmod = Path.chmodFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandsrc/redshift_comment_mcp/config.py:405 · File permission modification command — agent changes file ownership/permissionschmod leaves behind is a mode stricter than 0600 — never more permissive.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandtests/test_config.py:184 · File permission modification command — agent changes file ownership/permissionsreal_chmod = Path.chmodFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Privileged sudo commandtests/test_tools.py:2767 · Privileged sudo command — agent may execute with elevated privilegesread — mode 000, a root-owned file from a sudo install, a directoryFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈10,785 tok
7 files · 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

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

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Unclaimed publisher≈ +8 on the totalClaim kouko: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  4. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim koukoPropose a patch to the maintainer