Skills/PyPI/rm-mcp

rm-mcp@2.0.0

CAUTION· not started

Publisher claims: "MCP server for your reMarkable tablet: find, read, view and transcribe notes, send documents" Observed in sandbox: calls astral.sh only, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher thijs-verreck · publishing for 5 daysInstalls 491Last detonated 1 h ago

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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
REMARKABLE_TOKENConfiguration, not credentials: CANARY_VERBOSE, REMARKABLE_BACKGROUND_COLOR, REMARKABLE_BLOB_CACHE_DIR, REMARKABLE_COMPACT, REMARKABLE_INDEX_CONTENT, REMARKABLE_INDEX_PATH, REMARKABLE_INDEX_REBUILD, REMARKABLE_READ_ONLY, REMARKABLE_ROOT_PATH, REMARKABLE_WRITE_ROOT
Where it talks to
no vendor host named in the codeAlso remarkable.com, astral.sh, remarkable.engineering, thijsverreck.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · reached only astral.sh
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names remarkable.com, astral.sh, remarkable.engineering, thijsverreck.com as well as its own vendor. The guard injects REMARKABLE_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx rm-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 (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-16 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern; Pipe-to-shell pattern; Pipe-to-shell pattern. Summary: calls astral.sh only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 3 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.1snetworkCONNECT tcp://astral.sh:443 · not in the allow-list, refused
0.1sprocessexec /usr/bin/curl
0.1sprocessexited 1: ✗ uv did not install. Install it yourself: https://docs.astral.sh/uv/getting-started/installation/
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
0.2sprocesssecond launch, clock +45 days, CI unset
0.3snetworkCONNECT tcp://astral.sh:443 · not in the allow-list, refused
0.3sprocessexec /usr/bin/curl
0.3sprocessexited 1: ✗ uv did not install. Install it yourself: https://docs.astral.sh/uv/getting-started/installation/

Static findings

CRITICAL
Pipe-to-shell patternsetup.sh:27 · Pipe-to-shell pattern — downloads and immediately executes remote codecurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Remote installer piped to shellsetup.sh:27 · Remote installer piped to shellcurl -LsSf https://astral.sh/uv/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
CRITICAL
Pipe-to-shell patternsetup.sh:3 · Pipe-to-shell pattern — downloads and immediately executes remote code# Usage: curl -fsSL https://thijsverreck.com/setup.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
LOW
Fake instruction boundary tagdocs/development.md:152 · Fake instruction boundary tag · informational: not an instruction file<instructions>Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Remote installer piped to shellsetup.sh:3 · Remote installer piped to shell# Usage: curl -fsSL https://thijsverreck.com/setup.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
LOW
Fake instruction boundary tagdocs/development.md:154 · Fake instruction boundary tag · informational: not an instruction file</instructions>Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagemcpb/build.sh:12 · npx invocation of non-well-known package — may execute untrusted codenpx -y @anthropic-ai/mcpb validate manifest.jsonFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandrm_mcp/cli.py:177 · File permission modification command — agent changes file ownership/permissionsbad(f"{source.path} is readable by other users.", f"chmod 600 '{source.path}'")Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Pipe-to-shell patternCLAUDE.md:128 · Pipe-to-shell pattern — downloads and immediately executes remote codeUsage: `curl -fsSL https://thijsverreck.com/setup.sh | sh`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
LOW
Fake instruction boundary tagdocs/development.md:133 · Fake instruction boundary tag · informational: not an instruction file- **XML-structured docstrings** — Use `<usecase>`, `<instructions>`, `<parameters>`, `<examples>` tagsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagemcpb/build.sh:13 · npx invocation of non-well-known package — may execute untrusted codenpx -y @anthropic-ai/mcpb pack . "rm-mcp-$VERSION.mcpb"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Remote installer piped to shellCLAUDE.md:128 · Remote installer piped to shellUsage: `curl -fsSL https://thijsverreck.com/setup.sh | sh`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07

Cost to the agent

Instructions loaded
≈4,870 tok
2 files · 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

5 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 thijs-verreck: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  5. 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 thijs-verreckPropose a patch to the maintainer