Skills/PyPI/chemdraw-mcp

chemdraw-mcp@0.11.1

CAUTION· not started

Publisher claims: "Chemical structures, comparisons and reaction schemes as PNG/SVG via RDKit, with interactive data sheets. MVP by default; full profile optional. Unofficial, not affiliated with Revvity." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher jurimaxam-dotcom · publishing for 163 daysInstalls 2,938Last detonated 30 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 nih.gov, ebi.ac.uk, kegg.jp, uniprot.org, cas.org, astral.sh, rcsb.org — 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 chemdraw-mcp

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

What changed since 0.7.0

vet-skills diff chemdraw-mcp 0.7.0 0.11.1

This version reaches for something 0.7.0 did not: 2 new hosts (cas.org, rcsb.org). Compared from the two recorded runs, not from source.

New hosts
cas.org, rcsb.org

0.7.0 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 72/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; Hidden zero-width characters detected; HTML comment carrying imperative instructions to the agent. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.3sprocessdependency install exit 1 ·
0.3sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.3sprocessscript backend runs setup only
0.3sprocessno install scripts to re-run

Static findings

CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:65 · HTML comment carrying imperative instructions to the agentAufnahme: `npm --prefix chemdraw_tool/ui run readme:gifs -- lysozyme-cartoon` (Mol*-Cartoon, WebGL)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Hidden zero-width characters detectedchemdraw_tool/image_export.py:549 · Hidden zero-width characters detected — may conceal content"""Schreibt {format: inhalt} als base.<format> neben­einander.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:25 · HTML comment carrying imperative instructions to the agentHero: recorded with `npm --prefix chemdraw_tool/ui run readme:gifs` (panel test host, 600 px, light and dark).Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Privileged sudo commandchemdraw_tool/doctor.py:201 · Privileged sudo command — agent may execute with elevated privilegeselse "sudo apt install default-jre (or your distribution's JRE package)"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedchemdraw_tool/anki_export.py:311 · Python subprocess execution detectedsubprocess.run(["open", str(apkg_path)], check=True, timeout=10)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedchemdraw_tool/resolver.py:331 · Python subprocess execution detectedself._proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandchemdraw_tool/doctor.py:539 · File permission modification command — agent changes file ownership/permissionsfix=f'chmod u+rwx "{ancestor}"',Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedchemdraw_tool/chemdraw.py:88 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingchemdraw_tool/resolver.py:399 · Dynamic module loadingspec = importlib.util.find_spec("py2opsin")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedchemdraw_tool/chemdraw.py:105 · 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 detectedchemdraw_tool/chemdraw.py:114 · 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
npx invocation of non-well-known packagepyproject.toml:82 · npx invocation of non-well-known package — may execute untrusted code# startete gegen einen, den `npx playwright install` nie geholt hatte —Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedchemdraw_tool/chemdraw.py:123 · 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 detectedchemdraw_tool/chemdraw.py:81 · Python subprocess execution detectedresult = subprocess.run(["osascript", "-e", script], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedchemdraw_tool/resolver.py:283 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)chemdraw_tool/desktop_config.py:16 · MCP server using network transport (SSE/HTTP) — data sent over networkbereits konfigurierte MCP-Server oder Top-Level-Einstellungen anzufassen.Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
File permission modification commandchemdraw_tool/doctor.py:525 · File permission modification command — agent changes file ownership/permissionsfix=f'chmod u+rwx "{target}"',Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈83 tok
1 file · 81 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

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim jurimaxam-dotcom: 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. 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. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jurimaxam-dotcomPropose a patch to the maintainer