zotero-fulltext-mcp@0.16.1
CAUTION· not startedPublisher claims: "Convert a Zotero library's linked PDF attachments to Markdown, build a full-text search index, and expose it via an MCP server." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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 doi.org, crossref.org, datacite.org, sqlite.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.
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 2026-11-22 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: Hex-encoded string detected; Hidden zero-width characters detected. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
completed = subprocess.run([sys.executable, "-c", code], capture_output=True, text=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.@pytest.mark.parametrize("url", ["http://papers.example/paper.pdf", "https://u:[email protected]/paper.pdf"])Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if "PassageImageResult" not in globals() and importlib.util.find_spec("mcp") is not None:Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.convert_verified(config, run / "mapping_report.csv", output_dir=run,Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.if importlib.util.find_spec(module) is not NoneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell._JOURNAL_MAGIC = b"\xd9\xd5\x05\xf9\x20\xa1\x63\xd7"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.module = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.Popen(command, stdin=subprocess.DEVNULL, stdout=log, stderr=log,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.available = importlib.util.find_spec(module_name) is not NoneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.return subprocess.run([claude_exe, *claude_args], check=False).returncodeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.Popen( # type: ignore[call-overload]Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.completed = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(arguments, cwd=ROOT, env=env, check=check, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.Popen(args, creationflags=flags, **kwargs) # type: ignore[call-overload]Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.Popen(args, start_new_session=True, **kwargs) # type: ignore[call-overload]Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# subprocess.run(["claude", ...]) without shell=True does not, and fails withFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return "" + buffer.getvalue()Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
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 zotero-fulltext-mcp@0.16.1 as of 31 min 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%- Unclaimed publisher≈ +8 on the totalClaim matthiaskloft: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hex-encoded string detected≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- URL with embedded credentials≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.