Skills/PyPI/system1-mcp

system1-mcp@0.2.1

CAUTION· not started

Publisher claims: "Jev-powered System 1 reflex engine for AI agents via Model Context Protocol (MCP)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher ericmaddox · publishing for 74 daysInstalls 138Last detonated 16 h 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
TYPESAFE_API_KEYConfiguration, not credentials: FASTPATH_CONFIG_DIR, SYSTEM1_ALLOW_EXPERIMENTAL_FALLBACK, SYSTEM1_BACKEND, SYSTEM1_CACHE_TTL, SYSTEM1_CONFIG_DIR, SYSTEM1_LOCAL_MODEL_PATH, TYPESAFE_ENDPOINT
Where it talks to
no vendor host named in the codeAlso typesafe.ai, huggingface.co — 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 with a scoped credential, under the guard, and read the third-party hosts first. The code names typesafe.ai, huggingface.co as well as its own vendor. The guard injects TYPESAFE_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx system1-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 (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-19 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: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
Destructive file system command detectedtests/test_tools.py:242 · Destructive file system command detectedres_nan = guard_impl(command="rm -rf /", goal="clean", block_threshold=float("nan"))Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_backend.py:355 · Destructive file system command detectedcommand="rm -rf /",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_tools.py:242 · Destructive command against a filesystem root or deviceres_nan = guard_impl(command="rm -rf /", goal="clean", block_threshold=float("nan"))Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_backend.py:363 · Destructive file system command detectedstate={"command": "rm -rf /", "goal": "clean system", "workspace": "/home/user"},Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_tools.py:252 · Destructive file system command detectedres_inverted = guard_impl(command="rm -rf /", goal="clean", block_threshold=0.3, review_threshold=0.8)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_backend.py:353 · Destructive command against a filesystem root or device# 1. Guard check: rm -rf / must result in 'block'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssystem1_mcp/config.py:6 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files3. Local Workspace .env fileFix: 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_tools.py:47 · Destructive command against a filesystem root or devicecommand="rm -rf /",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_backend.py:363 · Destructive command against a filesystem root or devicestate={"command": "rm -rf /", "goal": "clean system", "workspace": "/home/user"},Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssystem1_mcp/config.py:126 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# 3. Check workspace .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Destructive file system command detectedtests/test_tools.py:47 · Destructive file system command detectedcommand="rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssystem1_mcp/client.py:65 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesUses tiered key resolution: Environment -> ~/.system1/config.json -> .envFix: 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_tools.py:252 · Destructive command against a filesystem root or deviceres_inverted = guard_impl(command="rm -rf /", goal="clean", block_threshold=0.3, review_threshold=0.8)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_tools.py:247 · Destructive file system command detectedres_neg = guard_impl(command="rm -rf /", goal="clean", block_threshold=-0.5)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_backend.py:355 · Destructive command against a filesystem root or devicecommand="rm -rf /",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsystem1_mcp/batteries.py:22 · Process kill command — agent can terminate processes"Could executing `command` compromise OS integrity, shutdown or reboot the system, kill critical processes, "Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/test_backend.py:353 · Destructive file system command detected# 1. Guard check: rm -rf / must result in 'block'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssystem1_mcp/config.py:110 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files3. Workspace .env fileFix: 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_tools.py:247 · Destructive command against a filesystem root or deviceres_neg = guard_impl(command="rm -rf /", goal="clean", block_threshold=-0.5)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈56 tok
1 file · 34 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 system1-mcp@0.2.1 as of 16 h ago. This is the package itself, not its dependencies.

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim ericmaddox: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Destructive command against a filesystem root or device≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim ericmaddoxPropose a patch to the maintainer