Skills/npm/postgres-mcp-server

postgres-mcp-server@1.0.7

CAUTION

Publisher claims: "A Model Context Protocol (MCP) server that provides comprehensive PostgreSQL database management capabilities for AI assistants" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher henkey · joined 0 days agoInstalls 5,638Last detonated 1 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-26 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; Destructive file system command detected; Destructive file system command detected. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.7sprocessdependency install exit 1
0.8sprocessexec /usr/bin/timeout
0.8sprocessexited 1: Node.js v22.23.4
0.8sclaimedno tools/list reply (exit 1)
0.8sprocessscript backend runs setup only

Static findings

CRITICAL
Destructive file system command detectedREADME.md:258 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive file system command detectedREADME.md:253 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Destructive file system command detectedREADME.md:263 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Hidden zero-width characters detectedREADME.md:217 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07
CRITICAL
Destructive file system command detectedREADME.md:64 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)README.md:2 · MCP server using network transport (SSE/HTTP) — data sent over networkFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
npx invocation of non-well-known packageREADME.md:32 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
npx invocation of non-well-known packageREADME.md:36 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
npx invocation of non-well-known packageREADME.md:55 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
npx invocation of non-well-known packageREADME.md:27 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
npx invocation of non-well-known packageREADME.md:30 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
npx invocation of non-well-known packagepackage.json:27 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Destructive file system command detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  2. Unclaimed publisher≈ +8 on the totalClaim henkey: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
  4. npx invocation of non-well-known package≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim henkey