Skills/PyPI/kalshi-mcp

kalshi-mcp@0.1.1

VERIFIED

Publisher claims: "MCP server for Kalshi prediction markets - search, analyze, and trade prediction markets through Claude Desktop" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher yakub268 · joined 0 days agoInstalls 116Last detonated 2 h ago
$claude mcp add kalshi-mcp -- uvx kalshi-mcp
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-05 and scored it 91/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. 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

Static findings

MEDIUM
Python subprocess execution detectedpublish.py:43 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

No other findings across 1,088 lines in 11 files.

Cost to the agent

Instructions loaded
≈63 tok
1 file · 11 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.

kalshi-mcp@0.1.1 safety verdict: Verified 91/100 — KillerSkills