Skills/npm/document-mcp

document-mcp@4.14.193

CAUTION

Publisher claims: "MCP (Model Context Protocol) server exposing documents.js's document-conversion, .odb, metadata, and font tooling as MCP tools." Observed in sandbox: static analysis only — behavior not yet observed.

Registry npm (MCP server)Publisher exadev · joined 0 days agoInstalls 29,770Last detonated 59 min ago
Dispute verdict

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
npx invocation of non-well-known packageREADME.md:116 · npx invocation of non-well-known package — may execute untrusted code
AST06
HIGH
Authorization escalation languageREADME.md:186 · Authorization escalation language
AST01
CRITICAL
Prompt injectionREADME.md:186 · Prompt injection — known jailbreak technique reference
AST01
HIGH
npx invocation of non-well-known packageREADME.md:181 · npx invocation of non-well-known package — may execute untrusted code
AST06
HIGH
npx invocation of non-well-known packageREADME.md:92 · npx invocation of non-well-known package — may execute untrusted code
AST06
HIGH
File permission modification commandREADME.md:192 · File permission modification command — agent changes file ownership/permissions
AST05
HIGH
npx invocation of non-well-known packageREADME.md:67 · npx invocation of non-well-known package — may execute untrusted code
AST06
HIGH
Auto-update or dynamic fetch configurationREADME.md:95 · Auto-update or dynamic fetch configuration — agent may load new code at runtime
AST06
CRITICAL
Context shift attemptREADME.md:186 · Context shift attempt — trying to change operational mode
AST01
document-mcp@4.14.193 safety verdict: Caution 56/100 — KillerSkills