Skills/PyPI/mcp-context-pipe

mcp-context-pipe@0.5.10

VERIFIED· not started

Publisher claims: "Universal switchboard for the Context-Pipe Protocol (CPP)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher luis-kobayashi · publishing for 194 daysInstalls 523Last detonated 7d ago
$claude mcp add mcp-context-pipe -- uvx mcp-context-pipe
WatchReport an issue

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: Verified 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

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Not enough was observed to say yet. Not started: dependency install failed; the server itself was not observed. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try mcp-context-pipe` runs it now and prints the full answer.

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 2026-11-07 and scored it 81/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'
0.2sprocessdependency install exit 1
0.2sprocessexec /usr/bin/date
0.2sprocessexec /usr/bin/timeout
0.2sprocessexec .venv/bin/context-pipe
0.2sclaimedno tools/list reply (exit 0)
0.2sprocessscript backend runs setup only
0.2sprocesssecond launch, clock +45 days, CI unset
0.2sprocessexec /usr/bin/faketime
0.2sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'

Static findings

HIGH
Access to sensitive file pathscontext_pipe/config_loader.py:23 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""Finds and loads a .env file from the current directory or parent directories into os.environ."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathscontext_pipe/config_loader.py:26 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdotenv_path = os.path.join(curr, ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedcontext_pipe/onboarding.py:280 · Python subprocess execution detectedproc = subprocess.run([sift_exe, "--version"], capture_output=True, text=True, timeout=15)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Destructive file system command detectedtests/test_dynamic.py:80 · Destructive file system command detectednodes = [{"cmd": "jq | rm -rf /", "args": []}]Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_config_loader.py:191 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdotenv_file = tmp_path / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_dynamic.py:80 · Destructive command against a filesystem root or devicenodes = [{"cmd": "jq | rm -rf /", "args": []}]Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_cli.py:187 · Destructive command against a filesystem root or devicenodes = json.dumps([{"cmd": "jq | rm -rf /"}])Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filescontext_pipe/onboarding.py:392 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file · informational: not an instruction file · informational: not an instruction filefound_paths.append(os.path.join(root, "AGENTS.md"))Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Destructive file system command detectedtests/test_cli.py:187 · Destructive file system command detectednodes = json.dumps([{"cmd": "jq | rm -rf /"}])Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_config_loader.py:187 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""load_dotenv_fallback loads .env variables into os.environ."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actioncontext_pipe/onboarding.py:1463 · File type combined with upload action — agent may exfiltrate local data files"Use this at any agent-to-agent handoff boundary to prevent context flooding.\\n1. Identify the output text from Agent A and the name of Agent B that will consume it.\\n2. Call `pipe_agent_handoff(outFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedcontext_pipe/scripts.py:32 · Python subprocess execution detectedprocess = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_config_loader.py:190 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Create a dummy .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/test_server.py:111 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesoutside_path = "/etc/passwd" if os.name != "nt" else "C:/Windows/System32/drivers/etc/hosts"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiontests/test_pipe_hook.py:64 · File type combined with upload action — agent may exfiltrate local data files"""When pipes.json does not exist, raw input must pass through unchanged."""Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈53 tok
1 file · 51 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

No advisories in OSV for mcp-context-pipe@0.5.10 as of 46 min ago. This is the package itself, not its dependencies.