Is plurnk-mcp@3.3.5 safe to install?

plurnk-mcp@3.3.5

VERIFIED· install only

Publisher claims: "Current Model Context Protocol host module for Plurnk." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher plurnk · publishing for 100 daysInstalls 2,794Last detonated 7d ago

$claude mcp add plurnk-mcp -- npx -y @plurnk/plurnk-mcp

Watch Report an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.

Tested: every file read, file written and host contacted by what ran
Not tested: use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-07 and scored it 82/100 (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 · 1 scenarios · 0 deviations

t+CategoryObserved action

0.0sprocessno install scripts in bundle

0.0sprocessscript backend runs setup only

0.0sprocessno install scripts to re-run

Static findings

HIGH

Access to sensitive file pathspackage.json:55 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files

"test:unit": "node --conditions=plurnk-dev --env-file=.env.defaults --env-file-if-exists=../plurnk-execs/.env.defaults --experimental-test-coverage --test-coverage-include-all '--test-coverage-include

Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.

AST05

MEDIUM

MCP server using network transport (SSE/HTTP)dist/client.d.ts:50 · MCP server using network transport (SSE/HTTP) — data sent over networkconstructor(definition: McpServerDefinition, environ?: NodeJS.ProcessEnv, options?: ServerConnectionOptions);Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.

AST04

HIGH

Access to sensitive file pathspackage.json:51 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env.defaults"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 pathspackage.json:56 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files

"test:intg": "node --conditions=plurnk-dev --env-file=.env.defaults --env-file-if-exists=../plurnk-execs/.env.defaults --experimental-test-coverage --test-coverage-include-all '--test-coverage-include

Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.

AST05

MEDIUM

MCP server using network transport (SSE/HTTP)dist/openWork.d.ts:23 · MCP server using network transport (SSE/HTTP) — data sent over network

export declare const assertWorkspaceDefinitionScope: (alias: string, definition: McpServerDefinition, workspaceName: string | undefined, environ: NodeJS.ProcessEnv) => void;

Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.

AST04

MEDIUM

MCP server using network transport (SSE/HTTP)dist/openWork.d.ts:20 · MCP server using network transport (SSE/HTTP) — data sent over network

export declare const rawWorkspaceBinding: (alias: string, definition: McpServerDefinition, environ: NodeJS.ProcessEnv) => string | readonly string[] | undefined;

Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.

AST04

MEDIUM

MCP server using network transport (SSE/HTTP)dist/openWork.d.ts:21 · MCP server using network transport (SSE/HTTP) — data sent over network

export declare const rawSessionBinding: (alias: string, definition: McpServerDefinition, environ: NodeJS.ProcessEnv) => string | undefined;

Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.

AST04

MEDIUM

Process kill commanddist/mcp-watchdog.mjs:7 · Process kill command — agent can terminate processes// wrapper can group-kill the whole tree, grandchildren included;Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

MCP server using network transport (SSE/HTTP)dist/openWork.d.ts:22 · MCP server using network transport (SSE/HTTP) — data sent over network

export declare const matchesWorkspaceBinding: (alias: string, definition: McpServerDefinition, environ: NodeJS.ProcessEnv, workspaceName: string | undefined) => boolean;

Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.

AST04

Cost to the agent

Instructions loaded

≈40 tok

1 file · 61 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for @plurnk/plurnk-mcp@3.3.5 as of 7d ago. This is the package itself, not its dependencies.