Security audit

AdsTurbo AI 视频生成 · AdsTurbo AI Video Generation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent AdsTurbo video-generation helper that uploads user-selected media and calls the AdsTurbo API, with privacy and dependency cautions but no hidden or destructive behavior found.

Install only if you are comfortable sending prompts, uploaded media, and generated task data to AdsTurbo. Treat uploaded images, audio, and videos as public-link assets, and do not upload sensitive personal, regulated, confidential, or copyrighted material unless you have permission and accept that risk. Prefer installing with a current patched requests version or a locked environment.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The document explicitly instructs users to upload local files so they become publicly accessible URLs, but it does not warn that this may expose sensitive images, audio, or videos to anyone with the link or to broader public access depending on backend behavior. In a skill that handles user-provided media, omission of privacy and data-exposure guidance increases the risk of unintended disclosure of personal or proprietary content.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The documentation explicitly tells users that image and video assets 'must be public URLs' and instructs them to upload local files first, but it does not warn that making assets public can expose sensitive or copyrighted media to unintended third parties. In a video-generation workflow, those assets are likely to contain proprietary creative content, personal imagery, or internal materials, so the omission creates a realistic privacy and data-leak risk.

Unpinned Dependencies

Low

Category: Supply Chain
Content: requests>=2.28.0
Confidence: 96% confidence
Finding: The dependency is specified with a lower bound only (requests>=2.28.0), which allows installation of different versions over time and makes builds non-reproducible. This increases supply-chain risk and can unintentionally permit installation of vulnerable or incompatible versions, especially if dependency resolution selects an older or newly compromised release.

Known Vulnerable Dependency: requests==2.28.0 — 8 advisory(ies): CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi); CVE-2026-25645 (Requests has Insecure Temp File Reuse in its extract_zipped_paths() utility func) +5 more

High

Category: Supply Chain
Confidence: 78% confidence
Finding: The requirement permits requests 2.28.0, a version with multiple known advisories, because the specifier is requests>=2.28.0 rather than excluding that vulnerable release. If dependency resolution installs 2.28.0 in any environment, the skill may be exposed to issues such as credential leakage, improper verification behavior, or other known flaws in a widely used HTTP client.

Static analysis

No suspicious patterns detected.