yaps-memory

• Outcome: Review
• Latest audit: Sep 24, 2026 · 2:25 AM UTC
• Version: 1.0.1

Overview

The skill is mostly coherent for Yaps vault notes, but its packaged runtime also exposes under-disclosed audio/video transcription and persistent meeting-project workflows.

Review before installing. Use it if you are comfortable with an agent invoking the local Yaps CLI, reading selected vault note content into the agent context, and potentially processing selected audio/video or creating Yaps meeting projects. Do not approve unexpected Keychain prompts, and avoid media workflows unless you intentionally want those local files processed by Yaps.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Rogue Agent: Self-Modification, Session Persistence
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection

Findings (17)

Description-Behavior Mismatch

High

• Confidence: 97% confidence
• Finding: The file exposes substantial capabilities for transcribing audio/video, generating subtitle files, extracting audio from video, and creating meeting transcription projects, which materially exceeds the declared skill purpose of finding or saving notes in a Yaps memory vault. Even though the implementation includes several safety checks, this is still dangerous because it expands the trusted attack surface and enables processing of local media and writing derived outputs to disk under a misleading or incomplete skill description.

Credential Access

High

• Category: Privilege Escalation

Content

function accountStatusUnsafeDiagnosis(appVersion) {
  return {
    code: "account_status_unsafe",
    message: `Yaps ${appVersion || "before 2.3.124"} uses an older credential-based account check, so this plugin deliberately did not run it. Update Yaps to 2.3.124 or newer; the plugin will then reuse the desktop sign-in, trial, or Yaps Pro automatically. Do not approve a Keychain prompt or create a separate plugin account.`,
  };
}

• Confidence: 70% confidence
• Finding: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Credential Access

High

• Category: Privilege Escalation

Content

function accountStatusUnsafeDiagnosis(appVersion) {
  return {
    code: "account_status_unsafe",
    message: `Yaps ${appVersion || "before 2.3.124"} uses an older credential-based account check, so this plugin deliberately did not run it. Update Yaps to 2.3.124 or newer; the plugin will then reuse the desktop sign-in, trial, or Yaps Pro automatically. Do not approve a Keychain prompt or create a separate plugin account.`,
  };
}

• Confidence: 70% confidence
• Finding: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Credential Access

High

• Category: Privilege Escalation

Content

function accountStatusUnsafeDiagnosis(appVersion) {
  return {
    code: "account_status_unsafe",
    message: `Yaps ${appVersion || "before 2.3.124"} uses an older credential-based account check, so this plugin deliberately did not run it. Update Yaps to 2.3.124 or newer; the plugin will then reuse the desktop sign-in, trial, or Yaps Pro automatically. Do not approve a Keychain prompt or create a separate plugin account.`,
  };
}

• Confidence: 70% confidence
• Finding: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Credential Access

High

• Category: Privilege Escalation

Content

function accountStatusUnsafeDiagnosis(appVersion) {
  return {
    code: "account_status_unsafe",
    message: `Yaps ${appVersion || "before 2.3.124"} uses an older credential-based account check, so this plugin deliberately did not run it. Update Yaps to 2.3.124 or newer; the plugin will then reuse the desktop sign-in, trial, or Yaps Pro automatically. Do not approve a Keychain prompt or create a separate plugin account.`,
  };
}

• Confidence: 70% confidence
• Finding: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Credential Access

High

• Category: Privilege Escalation

Content

message: "Yaps is signed in, but its trial or Yaps Pro access is not active. Open Yaps to review the available trial or Yaps Pro options; the plugin will pick up the change automatically.",
    };
  }
  if (auth.status === "credential_unavailable" || auth.diagnosticCode === "keychain_unavailable") {
    return {
      code: "account_status_unsupported",
      message: "This installed Yaps helper uses an older credential-based account check. Update Yaps and retry. Do not approve a Keychain prompt or create a separate plugin account.",

• Confidence: 70% confidence
• Finding: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 70% confidence
• Finding: Without declared permissions the skill's intent is opaque and cannot be validated.

Intent-Code Divergence

Medium

• Confidence: 94% confidence
• Finding: The comment states the adapter writes no diagnostics, credentials, settings, or host permissions, implying a no-write posture toward the host environment. However, later code creates temp directories and writes output files to user-specified locations and temporary paths, so the comment actively understates the adapter's write behavior.

Context-Inappropriate Capability

Medium

• Confidence: 89% confidence
• Finding: The meeting workflow can create persistent Yaps meeting projects and returns metadata such as project_path and audio_path, introducing persistence and disclosure of local filesystem information beyond a simple memory-vault note skill. In context, that mismatch is risky because users or hosts may authorize this skill expecting note lookup/save behavior, not media ingestion and project creation with persistent artifacts.

Session Persistence

Medium

• Category: Rogue Agent

Content

export const MIN_SAFE_AUTH_STATUS_VERSION = "2.3.124";
const MAX_PROBE_BYTES = 64 * 1024;
const MAX_VERSION_BYTES = 4 * 1024;
const MAX_PLIST_BYTES = 64 * 1024;
const MAX_WINDOWS_SHIM_BYTES = 4 * 1024;
const RUNNING_YAPS_PROCESS_NAMES = new Set(["yaps.exe", "yaps_mcp.exe", "yaps_cli.exe"]);
// Fixed WMI filter: never interpolate a discovered path into this command.

• Confidence: 75% confidence
• Finding: Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Session Persistence

Medium

• Category: Rogue Agent

Content

export const MIN_SAFE_AUTH_STATUS_VERSION = "2.3.124";
const MAX_PROBE_BYTES = 64 * 1024;
const MAX_VERSION_BYTES = 4 * 1024;
const MAX_PLIST_BYTES = 64 * 1024;
const MAX_WINDOWS_SHIM_BYTES = 4 * 1024;
const RUNNING_YAPS_PROCESS_NAMES = new Set(["yaps.exe", "yaps_mcp.exe", "yaps_cli.exe"]);
// Fixed WMI filter: never interpolate a discovered path into this command.

• Confidence: 75% confidence
• Finding: Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Session Persistence

Medium

• Category: Rogue Agent

Content

if (platform === "darwin") {
    const application = macApplicationForCli(cli.path, canonicalize);
    if (!application) return null;
    const plist = posix.join(application, "Contents", "Info.plist");
    try {
      const metadata = statFile(plist);
      if (!metadata.isFile() || metadata.size > MAX_PLIST_BYTES) return null;

• Confidence: 75% confidence
• Finding: Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Session Persistence

Medium

• Category: Rogue Agent

Content

if (platform === "darwin") {
    const application = macApplicationForCli(cli.path, canonicalize);
    if (!application) return null;
    const plist = posix.join(application, "Contents", "Info.plist");
    try {
      const metadata = statFile(plist);
      if (!metadata.isFile() || metadata.size > MAX_PLIST_BYTES) return null;

• Confidence: 75% confidence
• Finding: Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Session Persistence

Medium

• Category: Rogue Agent

Content

if (platform === "darwin") {
    const application = macApplicationForCli(cli.path, canonicalize);
    if (!application) return null;
    const plist = posix.join(application, "Contents", "Info.plist");
    try {
      const metadata = statFile(plist);
      if (!metadata.isFile() || metadata.size > MAX_PLIST_BYTES) return null;

• Confidence: 75% confidence
• Finding: Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Session Persistence

Medium

• Category: Rogue Agent

Content

if (platform === "darwin") {
    const application = macApplicationForCli(cli.path, canonicalize);
    if (!application) return null;
    const plist = posix.join(application, "Contents", "Info.plist");
    try {
      const metadata = statFile(plist);
      if (!metadata.isFile() || metadata.size > MAX_PLIST_BYTES) return null;

• Confidence: 75% confidence
• Finding: Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Session Persistence

Medium

• Category: Rogue Agent

Content

if (platform === "darwin") {
    const application = macApplicationForCli(cli.path, canonicalize);
    if (!application) return null;
    const plist = posix.join(application, "Contents", "Info.plist");
    try {
      const metadata = statFile(plist);
      if (!metadata.isFile() || metadata.size > MAX_PLIST_BYTES) return null;

• Confidence: 75% confidence
• Finding: Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Session Persistence

Medium

• Category: Rogue Agent

Content

if (platform === "darwin") {
    const application = macApplicationForCli(cli.path, canonicalize);
    if (!application) return null;
    const plist = posix.join(application, "Contents", "Info.plist");
    try {
      const metadata = statFile(plist);
      if (!metadata.isFile() || metadata.size > MAX_PLIST_BYTES) return null;

• Confidence: 75% confidence
• Finding: Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical

• Code: suspicious.dangerous_exec
• Location: runtime/run.mjs:74