Skills/npm/pi-mcp-extension

pi-mcp-extension@1.16.0

VERIFIED· install only

Publisher claims: "Full-featured, lightweight MCP extension for the Pi coding agent: stdio, SSE & Streamable HTTP transports, OAuth 2.1 (PKCE + DCR), lazy/eager lifecycles — minimal dependencies, zero bloat." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher irahardianto · publishing for 205 daysInstalls 1.1MLast detonated 32 min ago
$claude mcp add pi-mcp-extension -- npx -y pi-mcp-extension
WatchReport 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

What changed since 1.15.3

vet-skills diff pi-mcp-extension 1.15.3 1.16.0

In the sandbox, this version reached for nothing 1.15.3 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-22 and scored it 85/100 (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
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
MCP server using network transport (SSE/HTTP)src/mcp-servers-prompt.ts:52 · MCP server using network transport (SSE/HTTP) — data sent over networkexport interface RenderMcpServersSectionOptions {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)src/mcp-servers-prompt.ts:235 · MCP server using network transport (SSE/HTTP) — data sent over networkexport function renderMcpServersSection(Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
URL with embedded credentialssrc/secret-redaction.ts:65 · URL with embedded credentials — may be phishing or credential leaking/** `https://user:[email protected]/mcp` — userinfo credentials in a URL. */Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
File permission modification commandsrc/debug-log.ts:170 · File permission modification command — agent changes file ownership/permissions// WHY: Something removed `<agentDir>/logs` between the mkdir and the chmodFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)src/index.ts:256 · MCP server using network transport (SSE/HTTP) — data sent over networkconst section = renderMcpServersSection({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)src/index.ts:37 · MCP server using network transport (SSE/HTTP) — data sent over networkrenderMcpServersSection,Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Process kill commandsrc/stdio-process.ts:372 · Process kill command — agent can terminate processes// WHY: Windows has no `/proc` or `ps`, and the portable tree kill (`taskkill /T`)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)src/mcp-servers-prompt.ts:236 · MCP server using network transport (SSE/HTTP) — data sent over networkoptions: RenderMcpServersSectionOptions,Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Process kill commandsrc/stdio-process.ts:446 · Process kill command — agent can terminate processeskill: deps.kill ?? defaultDeps.kill,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈75 tok
1 file · 54 in bundle

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

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.