Back to skill

Security audit

Xpilot Ad Maker

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly does what it says, but it has a real credential-handling flaw and weak remote media download controls that users should review before installing.

Install only if you are comfortable giving it Vidu, Wavespeed, Replicate, and Cloudflare R2 credentials and having generated assets uploaded to an R2 public URL. Before use, restrict credentials to least-privilege accounts, validate the Wavespeed polling host before sending its token, add download limits and media validation, and prefer pinned dependencies with a lockfile.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (3)

T09 · Insecure Skill Coding Practices

Error
Location
lib/wavespeed.ts:41
Finding

Provider-Controlled Polling URL Can Receive the Wavespeed API Credential

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
make-xpilot-ad.ts:141
Finding

Unrestricted and Unbounded Download of Provider-Controlled Media

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
package.json:10
Finding

Executable Dependencies Are Not Reproducibly Pinned

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (22)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill description emphasizes ad generation but under-describes that it uses Cloudflare R2 credentials and uploads outputs to publicly hosted object storage. This can mislead users into exposing generated media and intermediate assets externally without fully understanding the data-flow or public accessibility.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The skill description emphasizes ad generation but under-describes that it uses Cloudflare R2 credentials and uploads outputs to publicly hosted object storage. This can mislead users into exposing generated media and intermediate assets externally without fully understanding the data-flow or public accessibility.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The skill description emphasizes ad generation but under-describes that it uses Cloudflare R2 credentials and uploads outputs to publicly hosted object storage. This can mislead users into exposing generated media and intermediate assets externally without fully understanding the data-flow or public accessibility.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The skill description emphasizes ad generation but under-describes that it uses Cloudflare R2 credentials and uploads outputs to publicly hosted object storage. This can mislead users into exposing generated media and intermediate assets externally without fully understanding the data-flow or public accessibility.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

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

Content

Scanner excerpt · make-xpilot-ad.ts (reported line 24)May include surrounding context.

ts
*/
import "dotenv/config";
import { config as loadEnv } from "dotenv";
loadEnv({ path: ".env.local" });

import { put } from "./lib/r2";
import { writeFileSync, readFileSync, mkdtempSync } from "fs";

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

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

Content

Scanner excerpt · xpilot-ad-finalize.ts (reported line 17)May include surrounding context.

ts
*/
import "dotenv/config";
import { config as loadEnv } from "dotenv";
loadEnv({ path: ".env.local" });

import { put } from "./lib/r2";
import { writeFileSync, readFileSync, mkdtempSync } from "fs";

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill declares required environment variables and clearly relies on networked third-party services, but it does not declare any explicit tool scope such as permissions or allowed-tools. That weakens least-privilege controls and makes it harder for a hosting agent to constrain secret access and outbound network use before execution.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The documentation does not prominently warn users that generated assets and final videos are uploaded to publicly hosted R2 URLs. In a skill handling media that may contain branding, likenesses, or sensitive business content, silent public publication can lead to privacy, confidentiality, and reputational harm.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
81% confidence
Finding

Using npx tsx without a pinned version allows resolution of whatever package version is current at execution time. That creates a supply-chain risk where a compromised or breaking upstream release could execute unexpected code on the operator's machine.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
81% confidence
Finding

The second npx tsx invocation has the same issue: it may fetch and run an unpinned package version at runtime. This increases exposure to dependency hijacking or malicious upstream releases.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · lib/wavespeed.ts (reported line 5)May include surrounding context.

ts
* Minimal Wavespeed.ai client for the protagonist reference image step.
 * Self-contained — only the t2i submit + poll path is implemented.
 */
const WAVESPEED_BASE = "https://api.wavespeed.ai/api/v3";

export interface WavespeedTask {
  id: string;

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · make-xpilot-ad.ts (reported line 44)May include surrounding context.

ts
process.exit(1);
}

const VIDU_BASE = "https://api.vidu.com/ent/v2";

// ─── Storyboard ─────────────────────────────────────────────────────────────

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 · xpilot-ad-finalize.ts (reported line 96)May include surrounding context.

ts
// Community models require version-based predictions endpoint.
  const KOKORO_VERSION =
    "f559560eb822dc509045f3921a1921234918b91739db4bf3daab2169b71c7a13";
  const res = await fetch("https://api.replicate.com/v1/predictions", {
    method: "POST",
    headers: {
      Authorization: `Token ${REPLICATE_KEY}`,

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · xpilot-ad-finalize.ts (reported line 96)May include surrounding context.

ts
// Community models require version-based predictions endpoint.
  const KOKORO_VERSION =
    "f559560eb822dc509045f3921a1921234918b91739db4bf3daab2169b71c7a13";
  const res = await fetch("https://api.replicate.com/v1/predictions", {
    method: "POST",
    headers: {
      Authorization: `Token ${REPLICATE_KEY}`,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
71% confidence
Finding

The file states that Replicate Kokoro TTS uses the af_bella voice, which imposes a specific voice/locale choice in the generated narration. There is no indication that users can opt into or change the language/voice selection, which may conflict with language or locale choice expectations.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 11)May include surrounding context.

json
"finalize": "tsx xpilot-ad-finalize.ts"
  },
  "dependencies": {
    "@aws-sdk/client-s3": "^3.700.0",
    "dotenv": "^17.0.0",
    "ffmpeg-static": "^5.3.0"
  },

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 12)May include surrounding context.

json
},
  "dependencies": {
    "@aws-sdk/client-s3": "^3.700.0",
    "dotenv": "^17.0.0",
    "ffmpeg-static": "^5.3.0"
  },
  "devDependencies": {

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 13)May include surrounding context.

json
"dependencies": {
    "@aws-sdk/client-s3": "^3.700.0",
    "dotenv": "^17.0.0",
    "ffmpeg-static": "^5.3.0"
  },
  "devDependencies": {
    "@types/node": "^20.0.0",

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 16)May include surrounding context.

json
"ffmpeg-static": "^5.3.0"
  },
  "devDependencies": {
    "@types/node": "^20.0.0",
    "tsx": "^4.21.0",
    "typescript": "^5.0.0"
  }

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 17)May include surrounding context.

json
},
  "devDependencies": {
    "@types/node": "^20.0.0",
    "tsx": "^4.21.0",
    "typescript": "^5.0.0"
  }
}

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 18)May include surrounding context.

json
"devDependencies": {
    "@types/node": "^20.0.0",
    "tsx": "^4.21.0",
    "typescript": "^5.0.0"
  }
}