Skills/PyPI/jevguard-mcp

jevguard-mcp@1.0.2

CAUTION

Publisher claims: "Official Model Context Protocol (MCP) server for JevGuard deterministic evaluation runtime." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher seb4ez · joined 0 days agoInstalls 394Last detonated 3 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-05 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: Privileged sudo command; Agent configured for autonomous execution without human approval. 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
0.3sprocessdependency install exit 1
0.3sprocessexec /usr/bin/timeout
0.3sprocessexec .venv/bin/jevguard-mcp
0.3sprocessexited 127: timeout: failed to run command '.venv/bin/jevguard-mcp': No such file or directory
0.3sclaimedno tools/list reply (exit 127)
0.3sprocessscript backend runs setup only

Static findings

HIGH
Privileged sudo commandjevguard_mcp/tools.py:1217 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandjevguard_mcp/tools.py:1694 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Agent configured for autonomous execution without human approvaljevguard_mcp/tools.py:1712 · Agent configured for autonomous execution without human approvalFix: Declare and request only the permissions the task needs.
AST02

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Agent configured for autonomous execution without human approval≈ +9 on the totalDeclare and request only the permissions the task needs.
  2. Unclaimed publisher≈ +8 on the totalClaim seb4ez: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. 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 seb4ez