messages-mcp@0.1.0
CAUTION· not startedPublisher claims: "Enables a voice assistant to read, draft, and send SMS and chat messages through the user's own Matrix inbox, integrated as a claude-voice plugin." 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 githubusercontent.com — 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 2026-11-21 and scored it 79/100 (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; HTML comment carrying imperative instructions to the agent; HTML comment carrying imperative instructions to the agent. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
msg = f"{path} can be read or changed by others; run chmod 600 on it"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.f" the file to tests/sms-since-answer.json with numbers written {PLACEHOLDER}, and put the new"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.A step that hangs even so is ended by hand with `kill -9 -- -<its pid>`, which the ratchetFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.sys.stderr.write(f"stopping {command[0]}; if it hangs, end it with: kill -9 -- -{step.pid}\n")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# A kill by some other test is not evidence about this rule.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.asked = subprocess.run([python, "-c", ASK], cwd=root, env=env, capture_output=True, text=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Made by scripts/docs.py from docs/setup.md. Change the guide, then run it.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.return subprocess.run(command, check=False).returncode # noqa: S603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(argv, check=True, capture_output=True, text=True, timeout=GH_TIMEOUT).stdoutFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["uv", "sync", "--locked", "--all-extras", "--quiet"], cwd=tree, env=env, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.not run: these are the gates; running them from a gate would recurseFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.return subprocess.run(["git", *args], cwd=ROOT, capture_output=True, text=True, check=True).stdoutFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.not run: these clean up a worktree, so they would remove the one the docs check runs inFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.return subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# turns colour back on, which would otherwise make every kill unattributable.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.step = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.QUOTES = str.maketrans(dict.fromkeys('\u201c\u201d"\u00ab\u00bb\u201e\u2039\u203a\u201a\u2018\u2019`', "'"))Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.r = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.code = subprocess.run(args, cwd=tree, env=env, check=False).returncodeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.A kill is not enough on its own. A mutation breaks whatever it breaks, and itFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim roykollensvendsen: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- 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.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.