Back to skill

Security audit

Fanqie Novel AI Video Drama Batch Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill’s video-generation purpose is coherent, but it under-discloses external data sharing and includes unsafe media-download and shell-execution patterns.

Review this skill carefully before installing. It may send parts of your novel or derived narration to KelingAI and ByteDance, download media from URLs those services return, and run ffmpeg locally. Avoid using confidential, unpublished, regulated, or client-owned text unless you accept those data flows and the runtime environment is sandboxed.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (3)

T09 · Insecure Skill Coding Practices

Error
Location
skill.js:68
Finding

Shell Command Injection Through an Unescaped Installation Path

Content
View full analysis
`file '${f}'`).join("\n")); const final = path.join(epDir, "final_video.mp4"); execSync(`ffmpeg -f concat -safe 0 -i "${list}" -i "${voice}" -c:v libx264 -c:a aac -y "${final}"`, { stdio: 'ignore' }); ``` ### Technical Analysis The skill constructs an FFmpeg command as a string and passes it to `execSync`. By default, `execSync` invokes a system shell. The `list`, `voice`, and `final` variables contain paths derived from `__dirname` through `rootOut` and `epDir`. Double quotes around these values do not make shell interpolation safe. If an attacker can influence the directory where the skill is installed or extracted, a directory name containing a double quote followed by shell syntax can terminate the quoted argument and append another command. No shell escaping or path-character validation is performed. The vulnerability is triggered when episode generation reaches the FFmpeg composition step. ### Attack Path 1. An attacker causes the skill package to be installed, extracted, or executed from a directory whose name contains shell metacharacters. 2. The malicious directory becomes part of `__dirname`. 3. `rootOut`, `epDir`, `list`, `voice`, and `final` inherit the malicious path. 4. The path is interpolated directly into the FFmpeg command string. 5. `execSync` passes the resulting string to the operating-system shell. 6. The shell interprets the injected syntax and executes the attacker's command when video composition begins. This path requires influence over the installation or execution directory. It is not directly exploitable through the novel text, `type`, or `style` parameters. ### Impact Assessment Successful exploitation provides arbitrary command execution ...[truncated 413 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
skill.js:50
Finding

Server-Side Request Forgery and Resource Exhaustion Through Unvalidated Media URLs

Content
View full analysis
Remediation
View remediation

other

Warning
Location
skill.js:147
Finding

User-Derived Narration Is Transmitted to an Undisclosed External TTS Provider

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (10)

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.js (reported line 128)May include surrounding context.

js
// 漫画视频
async function genManhua(prompt, style) {
  const r = await fetch("https://api.kelingai.com/v1/video/generate", {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ prompt: `${style}动漫分镜,9:16,流畅,${prompt}`, duration: 3 })

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.js (reported line 138)May include surrounding context.

js
// 漫画视频
async function genManhua(prompt, style) {
  const r = await fetch("https://api.kelingai.com/v1/video/generate", {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ prompt: `${style}动漫分镜,9:16,流畅,${prompt}`, duration: 3 })

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.js (reported line 128)May include surrounding context.

js
// 漫画视频
async function genManhua(prompt, style) {
  const r = await fetch("https://api.kelingai.com/v1/video/generate", {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ prompt: `${style}动漫分镜,9:16,流畅,${prompt}`, duration: 3 })

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.js (reported line 138)May include surrounding context.

js
// 漫画视频
async function genManhua(prompt, style) {
  const r = await fetch("https://api.kelingai.com/v1/video/generate", {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ prompt: `${style}动漫分镜,9:16,流畅,${prompt}`, duration: 3 })

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.js (reported line 148)May include surrounding context.

js
// 漫画视频
async function genManhua(prompt, style) {
  const r = await fetch("https://api.kelingai.com/v1/video/generate", {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ prompt: `${style}动漫分镜,9:16,流畅,${prompt}`, duration: 3 })

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

With no manifest available, the skill has no declared purpose that would justify its external video/image/TTS API calls and local ffmpeg execution. The code sends user-derived content to multiple third-party services and invokes a local binary to assemble media, which are materially powerful capabilities beyond a minimally inferable text-processing role.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

User-provided novel content is transformed into prompts and transmitted to a third-party video-generation service without any disclosure, consent, or data-handling controls visible in this file. That creates a privacy and data-governance risk because potentially sensitive or proprietary text may be exfiltrated to external vendors for processing.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.js (reported line 148)May include surrounding context.

js
// 封面
async function genCover(prompt) {
  const r = await fetch("https://api.kelingai.com/v1/image/generate", {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ prompt: `${prompt},竖屏封面,9:16,高清` })

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill sends narration text derived from user content to an external TTS provider without any user-facing notice or consent. If the input contains sensitive personal, confidential, or copyrighted material, this may violate privacy expectations and organizational data-handling requirements.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.js (reported line 158)May include surrounding context.

js
// 配音
async function genVoice(text, out) {
  const r = await fetch("https://openspeech.bytedance.com/api/v1/tts", {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ text, voice: "cute_female", format: "mp3" })