ClawHub
Back to skill

Security audit

yaps-transcription

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent local Yaps transcription skill with disclosed local file, desktop-session, and Yaps-managed persistence behavior.

Install only if you want a local Yaps desktop transcription bridge. Use it with media files you are comfortable letting Yaps and the agent host process, authorize any model downloads explicitly, and be aware that meeting mode may leave projects/audio inside Yaps. Do not approve unexpected Keychain prompts or create a separate plugin account.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (17)

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
84% confidence
Finding
The skill instructs the agent to invoke local code (`node <skill-root>/runtime/run.mjs`) and references runtime concepts like account readiness, local permissions, and file handling, but it does not declare any explicit tool scope such as `permissions` or `allowed-tools`. This creates a mismatch between documented behavior and declared restrictions, increasing the chance that an agent may access environment data or execute code without a clearly bounded authorization model.

Intent-Code Divergence

Medium
Confidence
87% confidence
Finding
The header comment states the adapter writes no diagnostics, credentials, settings, or host permissions, but later code explicitly invokes Yaps meeting workflows that may persist project data and audio (`meeting transcribe`, with comments acknowledging Yaps persists its own project audio). This mismatch can mislead reviewers or operators into approving the skill under an incomplete understanding of its data-handling behavior, which is a security/privacy concern.

Description-Behavior Mismatch

Medium
Confidence
94% confidence
Finding
The file implements `meetingFile()`, which goes beyond simple file-to-text transcription and can create persisted Yaps meeting projects, including optional audio extraction from video and project metadata handling. In a skill advertised as straightforward transcription, this is a broader capability surface that can surprise hosts or users and cause unintended data persistence, increasing privacy and governance risk even if the code is not overtly malicious.

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.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The code can automatically launch the installed Yaps desktop app during account recovery (`recoverAccount === true`) without any user-facing confirmation at the point of execution. Even though the launch target is constrained to expected installed locations, silently starting a GUI/background app can surprise users, trigger unintended network activity, or reuse an authenticated desktop session without explicit runtime consent.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

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