Back to skill

Security audit

Meet妙记纪要查询

Security checks for vulnerabilities and agentic risk

Overview

The skill reads your MioNote meetings as described, with disclosed credential storage and sharing of retrieved content with your AI assistant.

Use this only for meetings you are comfortable having your AI provider process. Enter the API key through the hidden terminal prompt, protect the saved credential, and remove sensitive transcript exports when finished. Local logout removes the stored key but does not revoke it; revoke or reset it in the MioNote app. The scanner's partial coverage was supplemented by reviewing all bundled executable code.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

md
下文的 `mionote` 都指本文件同目录下的 `scripts/mionote.mjs`,用本文件所在目录拼出绝对路径执行,例如

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/mionote.mjs (reported line 100)May include surrounding context.

js
import { chmodSync, mkdirSync, readFileSync, renameSync, rmSync, writeFileSync } from "node:fs";
import { homedir } from "node:os";
import { join } from "node:path";
var FILE_NAME = "credentials.json";
var KEY_PATTERN = /^msk-[A-Za-z0-9_-]{8,}$/;
function configDir(env = process.env, platform = process.platform, home = homedir()) {
  if (env.MIONOTE_CONFIG_DIR) return env.MIONOTE_CONFIG_DIR;

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.